speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update m2met2 doc & baseline (#675)

Browse Source 
* update doc

* update docs
This commit is contained in:
yhliang 2023-06-28 14:49:04 +08:00 committed by GitHub
parent a40e4210a7
commit 3cc7403b68
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
51 changed files with 595 additions and 2495 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
docs/m2met2/Challenge_result.md Normal file
View File

@ -0,0 +1,14 @@
# Challenge Result
The following table shows the final results of the competition, where Sub-track1 represents the sub-track under fixed training condition and Sub-track 2 represents the sub-track under the open training condition. All result in this table is cp-CER (%). The rankings in the table are the combined rankings of the two sub-tracks as all teams' submissions met the requirements of the sub-track under fixed training condition.
| Rank     | Team Name                             | Sub-track1     | Sub-track2     | paper |
|------|----------------------|------------|------------|------------------------|
| 1 | Ximalaya Speech Team | 11.27 | 11.27 | |
| 2 | 小马达 | 18.64 | 18.64 | |
| 3 | AIzyzx | 22.83 | 22.83 | |
| 4 | AsrSpeeder | / | 23.51 | |
| 5 | zyxlhz | 24.82 | 24.82 | |
| 6 | CMCAI | 26.11 | / | |
| 7 | Volcspeech | 34.21 | 34.21 | |
| 8 | 鉴往知来 | 40.14 | 40.14 | |
| 9 | baseline | 41.55 | 41.55 | |
| 10 | DAICT | 41.64 | | |

BIN
docs/m2met2/_build/doctrees/Challenge_result.doctree Normal file
View File

Binary file not shown.

BIN
docs/m2met2/_build/doctrees/environment.pickle
View File

Binary file not shown.

BIN
docs/m2met2/_build/doctrees/index.doctree
View File

Binary file not shown.

1
docs/m2met2/_build/html/Baseline.html
View File

@ -100,6 +100,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>

247
docs/m2met2/_build/html/Challenge_result.html Normal file
View File

@ -0,0 +1,247 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
<!-- Licensed under the Apache 2.0 License -->
<link rel="stylesheet" type="text/css" href="_static/fonts/open-sans/stylesheet.css" />
<!-- Licensed under the SIL Open Font License -->
<link rel="stylesheet" type="text/css" href="_static/fonts/source-serif-pro/source-serif-pro.css" />
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap.min.css" />
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Challenge Result &#8212; MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
<script src="_static/jquery.js"></script>
<script src="_static/underscore.js"></script>
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
<script src="_static/doctools.js"></script>
<script src="_static/sphinx_highlight.js"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="Organizers" href="Organizers.html" />
<link rel="prev" title="Rules" href="Rules.html" />
</head><body>
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="General Index"
accesskey="I">index</a></li>
<li class="right" >
<a href="Organizers.html" title="Organizers"
accesskey="N">next</a> |</li>
<li class="right" >
<a href="Rules.html" title="Rules"
accesskey="P">previous</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">Challenge Result</a></li>
</ul>
</div>
<div class="container-wrapper">
<div id="mobile-toggle">
<a href="#"><span class="glyphicon glyphicon-align-justify" aria-hidden="true"></span></a>
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
index.html" class="text-logo">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
<form class="form-inline" action="search.html" method="GET" role="form">
<div class="input-group">
<input name="q" type="text" class="form-control" placeholder="Search...">
</div>
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
</div>
<div class="sidebar-block">
<div class="sidebar-toc">
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="Introduction.html">Introduction</a><ul>
<li class="toctree-l2"><a class="reference internal" href="Introduction.html#call-for-participation">Call for participation</a></li>
<li class="toctree-l2"><a class="reference internal" href="Introduction.html#timeline-aoe-time">Timeline(AOE Time)</a></li>
<li class="toctree-l2"><a class="reference internal" href="Introduction.html#guidelines">Guidelines</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Dataset.html">Datasets</a><ul>
<li class="toctree-l2"><a class="reference internal" href="Dataset.html#overview-of-training-data">Overview of training data</a></li>
<li class="toctree-l2"><a class="reference internal" href="Dataset.html#detail-of-alimeeting-corpus">Detail of AliMeeting corpus</a></li>
<li class="toctree-l2"><a class="reference internal" href="Dataset.html#get-the-data">Get the data</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Track_setting_and_evaluation.html">Track &amp; Evaluation</a><ul>
<li class="toctree-l2"><a class="reference internal" href="Track_setting_and_evaluation.html#speaker-attributed-asr">Speaker-Attributed ASR</a></li>
<li class="toctree-l2"><a class="reference internal" href="Track_setting_and_evaluation.html#evaluation-metric">Evaluation metric</a></li>
<li class="toctree-l2"><a class="reference internal" href="Track_setting_and_evaluation.html#sub-track-arrangement">Sub-track arrangement</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Baseline.html">Baseline</a><ul>
<li class="toctree-l2"><a class="reference internal" href="Baseline.html#overview">Overview</a></li>
<li class="toctree-l2"><a class="reference internal" href="Baseline.html#quick-start">Quick start</a></li>
<li class="toctree-l2"><a class="reference internal" href="Baseline.html#baseline-results">Baseline results</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>
</div>
</div>
</div>
</div>
<div id="right-column">
<div role="navigation" aria-label="breadcrumbs navigation">
<ol class="breadcrumb">
<li><a href="index.html">Docs</a></li>
<li>Challenge Result</li>
</ol>
</div>
<div class="document clearer body">
<section id="challenge-result">
<h1>Challenge Result<a class="headerlink" href="#challenge-result" title="Permalink to this heading"></a></h1>
<p>The following table shows the final results of the competition, where Sub-track1 represents the sub-track under fixed training condition and Sub-track 2 represents the sub-track under the open training condition. All result in this table is cp-CER (%). The rankings in the table are the combined rankings of the two sub-tracks as all teams’ submissions met the requirements of the sub-track under fixed training condition.</p>
<table class="docutils align-default">
<thead>
<tr class="row-odd"><th class="head"><p>Rank    </p></th>
<th class="head"><p>Team Name                            </p></th>
<th class="head"><p>Sub-track1    </p></th>
<th class="head"><p>Sub-track2    </p></th>
<th class="head"><p>paper</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>1</p></td>
<td><p>Ximalaya Speech Team</p></td>
<td><p>11.27</p></td>
<td><p>11.27</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>2</p></td>
<td><p>小马达</p></td>
<td><p>18.64</p></td>
<td><p>18.64</p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>3</p></td>
<td><p>AIzyzx</p></td>
<td><p>22.83</p></td>
<td><p>22.83</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>4</p></td>
<td><p>AsrSpeeder</p></td>
<td><p>/</p></td>
<td><p>23.51</p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>5</p></td>
<td><p>zyxlhz</p></td>
<td><p>24.82</p></td>
<td><p>24.82</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>6</p></td>
<td><p>CMCAI</p></td>
<td><p>26.11</p></td>
<td><p>/</p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>7</p></td>
<td><p>Volcspeech</p></td>
<td><p>34.21</p></td>
<td><p>34.21</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>8</p></td>
<td><p>鉴往知来</p></td>
<td><p>40.14</p></td>
<td><p>40.14</p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>9</p></td>
<td><p>baseline</p></td>
<td><p>41.55</p></td>
<td><p>41.55</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>10</p></td>
<td><p>DAICT</p></td>
<td><p>41.64</p></td>
<td><p></p></td>
<td><p></p></td>
</tr>
</tbody>
</table>
</section>
</div>
<div class="footer-relations">
<div class="pull-left">
<a class="btn btn-default" href="Rules.html" title="previous chapter (use the left arrow)">Rules</a>
</div>
<div class="pull-right">
<a class="btn btn-default" href="Organizers.html" title="next chapter (use the right arrow)">Organizers</a>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="clearfix"></div>
</div>
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="General Index"
>index</a></li>
<li class="right" >
<a href="Organizers.html" title="Organizers"
>next</a> |</li>
<li class="right" >
<a href="Rules.html" title="Rules"
>previous</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">Challenge Result</a></li>
</ul>
</div>
<script type="text/javascript">
$("#mobile-toggle a").click(function () {
$("#left-column").toggle();
});
</script>
<script type="text/javascript" src="_static/js/bootstrap.js"></script>
<div class="footer">
&copy; Copyright 2023, Speech Lab, Alibaba Group; ASLP Group, Northwestern Polytechnical University. Created using <a href="http://sphinx.pocoo.org/">Sphinx</a>.
</div>
</body>
</html>

1
docs/m2met2/_build/html/Contact.html
View File

@ -96,6 +96,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Contact</a></li>
</ul>

1
docs/m2met2/_build/html/Dataset.html
View File

@ -101,6 +101,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>

1
docs/m2met2/_build/html/Introduction.html
View File

@ -101,6 +101,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>

9
docs/m2met2/_build/html/Organizers.html
View File

@ -27,7 +27,7 @@
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="Contact" href="Contact.html" />
<link rel="prev" title="Rules" href="Rules.html" />
<link rel="prev" title="Challenge Result" href="Challenge_result.html" />
@ -42,7 +42,7 @@
<a href="Contact.html" title="Contact"
accesskey="N">next</a> |</li>
<li class="right" >
<a href="Rules.html" title="Rules"
<a href="Challenge_result.html" title="Challenge Result"
accesskey="P">previous</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">Organizers</a></li>
@ -100,6 +100,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>
@ -156,7 +157,7 @@ Email: <a class="reference external" href="mailto:sly&#46;zsl&#37;&#52;&#48;alib
<div class="footer-relations">
<div class="pull-left">
<a class="btn btn-default" href="Rules.html" title="previous chapter (use the left arrow)">Rules</a>
<a class="btn btn-default" href="Challenge_result.html" title="previous chapter (use the left arrow)">Challenge Result</a>
</div>
<div class="pull-right">
@ -178,7 +179,7 @@ Email: <a class="reference external" href="mailto:sly&#46;zsl&#37;&#52;&#48;alib
<a href="Contact.html" title="Contact"
>next</a> |</li>
<li class="right" >
<a href="Rules.html" title="Rules"
<a href="Challenge_result.html" title="Challenge Result"
>previous</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">Organizers</a></li>

9
docs/m2met2/_build/html/Rules.html
View File

@ -26,7 +26,7 @@
<script src="_static/sphinx_highlight.js"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="Organizers" href="Organizers.html" />
<link rel="next" title="Challenge Result" href="Challenge_result.html" />
<link rel="prev" title="Baseline" href="Baseline.html" />
@ -39,7 +39,7 @@
<a href="genindex.html" title="General Index"
accesskey="I">index</a></li>
<li class="right" >
<a href="Organizers.html" title="Organizers"
<a href="Challenge_result.html" title="Challenge Result"
accesskey="N">next</a> |</li>
<li class="right" >
<a href="Baseline.html" title="Baseline"
@ -100,6 +100,7 @@
</ul>
</li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>
@ -145,7 +146,7 @@
</div>
<div class="pull-right">
<a class="btn btn-default" href="Organizers.html" title="next chapter (use the right arrow)">Organizers</a>
<a class="btn btn-default" href="Challenge_result.html" title="next chapter (use the right arrow)">Challenge Result</a>
</div>
</div>
<div class="clearer"></div>
@ -160,7 +161,7 @@
<a href="genindex.html" title="General Index"
>index</a></li>
<li class="right" >
<a href="Organizers.html" title="Organizers"
<a href="Challenge_result.html" title="Challenge Result"
>next</a> |</li>
<li class="right" >
<a href="Baseline.html" title="Baseline"

1
docs/m2met2/_build/html/Track_setting_and_evaluation.html
View File

@ -101,6 +101,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>

14
docs/m2met2/_build/html/_sources/Challenge_result.md.txt Normal file
View File

@ -0,0 +1,14 @@
# Challenge Result
The following table shows the final results of the competition, where Sub-track1 represents the sub-track under fixed training condition and Sub-track 2 represents the sub-track under the open training condition. All result in this table is cp-CER (%). The rankings in the table are the combined rankings of the two sub-tracks as all teams' submissions met the requirements of the sub-track under fixed training condition.
| Rank &nbsp; &nbsp; | Team Name &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; | Sub-track1 &nbsp; &nbsp; | Sub-track2 &nbsp; &nbsp; | paper |
|------|----------------------|------------|------------|------------------------|
| 1 | Ximalaya Speech Team | 11.27 | 11.27 | |
| 2 | 小马达 | 18.64 | 18.64 | |
| 3 | AIzyzx | 22.83 | 22.83 | |
| 4 | AsrSpeeder | / | 23.51 | |
| 5 | zyxlhz | 24.82 | 24.82 | |
| 6 | CMCAI | 26.11 | / | |
| 7 | Volcspeech | 34.21 | 34.21 | |
| 8 | 鉴往知来 | 40.14 | 40.14 | |
| 9 | baseline | 41.55 | 41.55 | |
| 10 | DAICT | 41.64 | | |

1
docs/m2met2/_build/html/_sources/index.rst.txt
View File

@ -18,5 +18,6 @@ To facilitate reproducible research, we provide a comprehensive overview of the
./Track_setting_and_evaluation
./Baseline
./Rules
./Challenge_result
./Organizers
./Contact

1
docs/m2met2/_build/html/genindex.html
View File

@ -91,6 +91,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>

2
docs/m2met2/_build/html/index.html
View File

@ -96,6 +96,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>
@ -131,6 +132,7 @@ To facilitate reproducible research, we provide a comprehensive overview of the
<li class="toctree-l1"><a class="reference internal" href="Track_setting_and_evaluation.html">Track &amp; Evaluation</a></li>
<li class="toctree-l1"><a class="reference internal" href="Baseline.html">Baseline</a></li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>

BIN
docs/m2met2/_build/html/objects.inv
View File

Binary file not shown.

1
docs/m2met2/_build/html/search.html
View File

@ -84,6 +84,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="Rules.html">Rules</a></li>
<li class="toctree-l1"><a class="reference internal" href="Challenge_result.html">Challenge Result</a></li>
<li class="toctree-l1"><a class="reference internal" href="Organizers.html">Organizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="Contact.html">Contact</a></li>
</ul>

2
docs/m2met2/_build/html/searchindex.js
View File

File diff suppressed because one or more lines are too long

1
docs/m2met2/index.rst
View File

@ -18,5 +18,6 @@ To facilitate reproducible research, we provide a comprehensive overview of the
./Track_setting_and_evaluation
./Baseline
./Rules
./Challenge_result
./Organizers
./Contact

BIN
docs/m2met2_cn/_build/doctrees/environment.pickle
View File

Binary file not shown.

BIN
docs/m2met2_cn/_build/doctrees/index.doctree
View File

Binary file not shown.

BIN
docs/m2met2_cn/_build/doctrees/比赛结果.doctree Normal file
View File

Binary file not shown.

1
docs/m2met2_cn/_build/html/_sources/index.rst.txt
View File

@ -18,5 +18,6 @@ ASRU 2023 多通道多方会议转录挑战 2.0
./赛道设置与评估
./基线
./规则
./比赛结果
./组委会
./联系方式

14
docs/m2met2_cn/_build/html/_sources/比赛结果.md.txt Normal file
View File

@ -0,0 +1,14 @@
# 比赛结果
表中为本次竞赛的最终结果，其中Sub-track1代表限定数据子赛道，Sub-track2代表非限定数据子赛道。表中数据均为cp-CER（%）。由于所有队伍的提交均符合限定数据子赛道的要求，表中的排名为两个字赛道合并后的排名。
| 排名 &nbsp; &nbsp; |队伍名称 &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; | 子赛道一 &nbsp; &nbsp; | 子赛道二 &nbsp; &nbsp; | 论文 &nbsp; &nbsp; |
|------|----------------------|------------|------------|------------------------|
| 1 | Ximalaya Speech Team | 11.27 | 11.27 | |
| 2 | 小马达 | 18.64 | 18.64 | |
| 3 | AIzyzx | 22.83 | 22.83 | |
| 4 | AsrSpeeder | / | 23.51 | |
| 5 | zyxlhz | 24.82 | 24.82 | |
| 6 | CMCAI | 26.11 | / | |
| 7 | Volcspeech | 34.21 | 34.21 | |
| 8 | 鉴往知来 | 40.14 | 40.14 | |
| 9 | baseline | 41.55 | 41.55 | |
| 10 | DAICT | 41.64 | | |

1
docs/m2met2_cn/_build/html/genindex.html
View File

@ -92,6 +92,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>

2
docs/m2met2_cn/_build/html/index.html
View File

@ -97,6 +97,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>
@ -132,6 +133,7 @@
<li class="toctree-l1"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html">赛道设置与评估</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E5%9F%BA%E7%BA%BF.html">基线</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>

BIN
docs/m2met2_cn/_build/html/objects.inv
View File

Binary file not shown.

1
docs/m2met2_cn/_build/html/search.html
View File

@ -85,6 +85,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>

2
docs/m2met2_cn/_build/html/searchindex.js
View File

@ -1 +1 @@
Search.setIndex({"docnames": ["index", "\u57fa\u7ebf", "\u6570\u636e\u96c6", "\u7b80\u4ecb", "\u7ec4\u59d4\u4f1a", "\u8054\u7cfb\u65b9\u5f0f", "\u89c4\u5219", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30"], "filenames": ["index.rst", "\u57fa\u7ebf.md", "\u6570\u636e\u96c6.md", "\u7b80\u4ecb.md", "\u7ec4\u59d4\u4f1a.md", "\u8054\u7cfb\u65b9\u5f0f.md", "\u89c4\u5219.md", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30.md"], "titles": ["ASRU 2023 \u591a\u901a\u9053\u591a\u65b9\u4f1a\u8bae\u8f6c\u5f55\u6311\u6218 2.0", "\u57fa\u7ebf", "\u6570\u636e\u96c6", "\u7b80\u4ecb", "\u7ec4\u59d4\u4f1a", "\u8054\u7cfb\u65b9\u5f0f", "\u7ade\u8d5b\u89c4\u5219", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30"], "terms": {"m2met": [0, 1, 3, 5, 7], "asru2023": [0, 3], "m2met2": [0, 3, 5, 7], "funasr": 1, "sa": 1, "asr": [1, 3, 7], "speakerencod": 1, "modelscop": [1, 7], "instal": 1, "run": 1, "sh": 1, "run_m2met_2023_inf": 1, "alimeet": [1, 3, 5, 7], "dataset": 1, "eval_ali_far": 1, "eval_ali_near": 1, "test_ali_far": 1, "test_ali_near": 1, "train_ali_far": 1, "train_ali_near": 1, "test_2023_ali_far": 1, "16": [1, 3], "wav": 1, "scp": 1, "wav_raw": 1, "segment": 1, "utt2spk": 1, "spk2utt": 1, "data": 1, "aishel": [2, 7], "cn": [2, 4, 7], "celeb": [2, 7], "test": [2, 6, 7], "2023": [2, 3, 6, 7], "118": 2, "75": 2, "104": 2, "train": 2, "eval": [2, 6], "10": [2, 3, 7], "212": 2, "15": 2, "30": 2, "456": 2, "25": 2, "13": 2, "55": 2, "42": 2, "27": 2, "34": 2, "76": 2, "20": [2, 3], "textgrid": 2, "id": 2, "openslr": 2, "baselin": 2, "automat": 3, "speech": 3, "recognit": 3, "speaker": 3, "diariz": 3, "rich": 3, "transcript": 3, "evalu": 3, "chime": 3, "comput": 3, "hear": 3, "in": 3, "multisourc": 3, "environ": 3, "misp": 3, "multimod": 3, "inform": 3, "base": 3, "process": 3, "multi": 3, "channel": 3, "parti": 3, "meet": 3, "iassp2022": 3, "asru": 3, "29": 3, "11": 3, "22": 3, "26": 3, "session": 3, "12": 3, "workshop": 3, "challeng": 3, "gmail": [3, 5], "com": [3, 4, 5], "lxie": 4, "nwpu": 4, "edu": 4, "kong": 4, "aik": 4, "lee": 4, "star": 4, "kongaik": 4, "ieee": 4, "org": 4, "zhiji": 4, "yzj": 4, "alibaba": 4, "inc": 4, "sli": 4, "zsl": 4, "yanminqian": 4, "sjtu": 4, "zhuc": 4, "microsoft": 4, "wujian": 4, "ceo": 4, "buhui": 4, "aishelldata": 4, "cpcer": [6, 7], "las": 6, "rnnt": 6, "transform": 6, "aishell4": 7, "vad": 7, "cer": 7, "ins": 7, "sub": 7, "del": 7, "text": 7, "frac": 7, "mathcal": 7, "n_": 7, "total": 7, "time": 7, "100": 7, "hug": 7, "face": 7}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"asru": 0, "2023": 0, "alimeet": 2, "aoe": 3}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"ASRU 2023 \u591a\u901a\u9053\u591a\u65b9\u4f1a\u8bae\u8f6c\u5f55\u6311\u6218 2.0": [[0, "asru-2023-2-0"]], "\u76ee\u5f55:": [[0, null]], "\u57fa\u7ebf": [[1, "id1"]], "\u57fa\u7ebf\u6982\u8ff0": [[1, "id2"]], "\u5feb\u901f\u5f00\u59cb": [[1, "id3"]], "\u57fa\u7ebf\u7ed3\u679c": [[1, "id4"]], "\u6570\u636e\u96c6": [[2, "id1"]], "\u6570\u636e\u96c6\u6982\u8ff0": [[2, "id2"]], "Alimeeting\u6570\u636e\u96c6\u4ecb\u7ecd": [[2, "alimeeting"]], "\u83b7\u53d6\u6570\u636e": [[2, "id3"]], "\u7b80\u4ecb": [[3, "id1"]], "\u7ade\u8d5b\u4ecb\u7ecd": [[3, "id2"]], "\u65f6\u95f4\u5b89\u6392(AOE\u65f6\u95f4)": [[3, "aoe"]], "\u7ade\u8d5b\u62a5\u540d": [[3, "id3"]], "\u7ec4\u59d4\u4f1a": [[4, "id1"]], "\u8054\u7cfb\u65b9\u5f0f": [[5, "id1"]], "\u7ade\u8d5b\u89c4\u5219": [[6, "id1"]], "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30": [[7, "id1"]], "\u8bf4\u8bdd\u4eba\u76f8\u5173\u7684\u8bed\u97f3\u8bc6\u522b": [[7, "id2"]], "\u8bc4\u4f30\u65b9\u6cd5": [[7, "id3"]], "\u5b50\u8d5b\u9053\u8bbe\u7f6e": [[7, "id4"]], "\u5b50\u8d5b\u9053\u4e00 (\u9650\u5b9a\u8bad\u7ec3\u6570\u636e):": [[7, "id5"]], "\u5b50\u8d5b\u9053\u4e8c (\u5f00\u653e\u8bad\u7ec3\u6570\u636e):": [[7, "id6"]]}, "indexentries": {}})
Search.setIndex({"docnames": ["index", "\u57fa\u7ebf", "\u6570\u636e\u96c6", "\u6bd4\u8d5b\u7ed3\u679c", "\u7b80\u4ecb", "\u7ec4\u59d4\u4f1a", "\u8054\u7cfb\u65b9\u5f0f", "\u89c4\u5219", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30"], "filenames": ["index.rst", "\u57fa\u7ebf.md", "\u6570\u636e\u96c6.md", "\u6bd4\u8d5b\u7ed3\u679c.md", "\u7b80\u4ecb.md", "\u7ec4\u59d4\u4f1a.md", "\u8054\u7cfb\u65b9\u5f0f.md", "\u89c4\u5219.md", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30.md"], "titles": ["ASRU 2023 \u591a\u901a\u9053\u591a\u65b9\u4f1a\u8bae\u8f6c\u5f55\u6311\u6218 2.0", "\u57fa\u7ebf", "\u6570\u636e\u96c6", "\u6bd4\u8d5b\u7ed3\u679c", "\u7b80\u4ecb", "\u7ec4\u59d4\u4f1a", "\u8054\u7cfb\u65b9\u5f0f", "\u7ade\u8d5b\u89c4\u5219", "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30"], "terms": {"m2met": [0, 1, 4, 6, 8], "asru2023": [0, 4], "m2met2": [0, 4, 6, 8], "funasr": 1, "sa": 1, "asr": [1, 4, 8], "speakerencod": 1, "modelscop": [1, 8], "instal": 1, "run": 1, "sh": 1, "run_m2met_2023_inf": 1, "alimeet": [1, 4, 6, 8], "dataset": 1, "eval_ali_far": 1, "eval_ali_near": 1, "test_ali_far": 1, "test_ali_near": 1, "train_ali_far": 1, "train_ali_near": 1, "test_2023_ali_far": 1, "16": [1, 4], "wav": 1, "scp": 1, "wav_raw": 1, "segment": 1, "utt2spk": 1, "spk2utt": 1, "data": 1, "aishel": [2, 8], "cn": [2, 5, 8], "celeb": [2, 8], "test": [2, 7, 8], "2023": [2, 4, 7, 8], "118": 2, "75": 2, "104": 2, "train": 2, "eval": [2, 7], "10": [2, 3, 4, 8], "212": 2, "15": 2, "30": 2, "456": 2, "25": 2, "13": 2, "55": [2, 3], "42": 2, "27": [2, 3], "34": [2, 3], "76": 2, "20": [2, 4], "textgrid": 2, "id": 2, "openslr": 2, "baselin": [2, 3], "sub": [3, 8], "track1": 3, "track2": 3, "cp": 3, "cer": [3, 8], "ximalaya": 3, "speech": [3, 4], "team": 3, "11": [3, 4], "18": 3, "64": 3, "aizyzx": 3, "22": [3, 4], "83": 3, "asrspeed": 3, "23": 3, "51": 3, "zyxlhz": 3, "24": 3, "82": 3, "cmcai": 3, "26": [3, 4], "volcspeech": 3, "21": 3, "40": 3, "14": 3, "41": 3, "daict": 3, "automat": 4, "recognit": 4, "speaker": 4, "diariz": 4, "rich": 4, "transcript": 4, "evalu": 4, "chime": 4, "comput": 4, "hear": 4, "in": 4, "multisourc": 4, "environ": 4, "misp": 4, "multimod": 4, "inform": 4, "base": 4, "process": 4, "multi": 4, "channel": 4, "parti": 4, "meet": 4, "iassp2022": 4, "asru": 4, "29": 4, "session": 4, "12": 4, "workshop": 4, "challeng": 4, "gmail": [4, 6], "com": [4, 5, 6], "lxie": 5, "nwpu": 5, "edu": 5, "kong": 5, "aik": 5, "lee": 5, "star": 5, "kongaik": 5, "ieee": 5, "org": 5, "zhiji": 5, "yzj": 5, "alibaba": 5, "inc": 5, "sli": 5, "zsl": 5, "yanminqian": 5, "sjtu": 5, "zhuc": 5, "microsoft": 5, "wujian": 5, "ceo": 5, "buhui": 5, "aishelldata": 5, "cpcer": [7, 8], "las": 7, "rnnt": 7, "transform": 7, "aishell4": 8, "vad": 8, "ins": 8, "del": 8, "text": 8, "frac": 8, "mathcal": 8, "n_": 8, "total": 8, "time": 8, "100": 8, "hug": 8, "face": 8}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"asru": 0, "2023": 0, "alimeet": 2, "aoe": 4}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"ASRU 2023 \u591a\u901a\u9053\u591a\u65b9\u4f1a\u8bae\u8f6c\u5f55\u6311\u6218 2.0": [[0, "asru-2023-2-0"]], "\u76ee\u5f55:": [[0, null]], "\u57fa\u7ebf": [[1, "id1"]], "\u57fa\u7ebf\u6982\u8ff0": [[1, "id2"]], "\u5feb\u901f\u5f00\u59cb": [[1, "id3"]], "\u57fa\u7ebf\u7ed3\u679c": [[1, "id4"]], "\u6570\u636e\u96c6": [[2, "id1"]], "\u6570\u636e\u96c6\u6982\u8ff0": [[2, "id2"]], "Alimeeting\u6570\u636e\u96c6\u4ecb\u7ecd": [[2, "alimeeting"]], "\u83b7\u53d6\u6570\u636e": [[2, "id3"]], "\u6bd4\u8d5b\u7ed3\u679c": [[3, "id1"]], "\u7b80\u4ecb": [[4, "id1"]], "\u7ade\u8d5b\u4ecb\u7ecd": [[4, "id2"]], "\u65f6\u95f4\u5b89\u6392(AOE\u65f6\u95f4)": [[4, "aoe"]], "\u7ade\u8d5b\u62a5\u540d": [[4, "id3"]], "\u7ec4\u59d4\u4f1a": [[5, "id1"]], "\u8054\u7cfb\u65b9\u5f0f": [[6, "id1"]], "\u7ade\u8d5b\u89c4\u5219": [[7, "id1"]], "\u8d5b\u9053\u8bbe\u7f6e\u4e0e\u8bc4\u4f30": [[8, "id1"]], "\u8bf4\u8bdd\u4eba\u76f8\u5173\u7684\u8bed\u97f3\u8bc6\u522b": [[8, "id2"]], "\u8bc4\u4f30\u65b9\u6cd5": [[8, "id3"]], "\u5b50\u8d5b\u9053\u8bbe\u7f6e": [[8, "id4"]], "\u5b50\u8d5b\u9053\u4e00 (\u9650\u5b9a\u8bad\u7ec3\u6570\u636e):": [[8, "id5"]], "\u5b50\u8d5b\u9053\u4e8c (\u5f00\u653e\u8bad\u7ec3\u6570\u636e):": [[8, "id6"]]}, "indexentries": {}})

1
docs/m2met2_cn/_build/html/基线.html
View File

@ -101,6 +101,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>

1
docs/m2met2_cn/_build/html/数据集.html
View File

@ -101,6 +101,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>

248
docs/m2met2_cn/_build/html/比赛结果.html Normal file
View File

@ -0,0 +1,248 @@
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
<!-- Licensed under the Apache 2.0 License -->
<link rel="stylesheet" type="text/css" href="_static/fonts/open-sans/stylesheet.css" />
<!-- Licensed under the SIL Open Font License -->
<link rel="stylesheet" type="text/css" href="_static/fonts/source-serif-pro/source-serif-pro.css" />
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap.min.css" />
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>比赛结果 &#8212; 多通道多方会议转录挑战2.0</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
<script src="_static/jquery.js"></script>
<script src="_static/underscore.js"></script>
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
<script src="_static/doctools.js"></script>
<script src="_static/sphinx_highlight.js"></script>
<script src="_static/translations.js"></script>
<link rel="index" title="索引" href="genindex.html" />
<link rel="search" title="搜索" href="search.html" />
<link rel="next" title="组委会" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" />
<link rel="prev" title="竞赛规则" href="%E8%A7%84%E5%88%99.html" />
</head><body>
<div class="related" role="navigation" aria-label="related navigation">
<h3>导航</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="总索引"
accesskey="I">索引</a></li>
<li class="right" >
<a href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" title="组委会"
accesskey="N">下一页</a> |</li>
<li class="right" >
<a href="%E8%A7%84%E5%88%99.html" title="竞赛规则"
accesskey="P">上一页</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">多通道多方会议转录挑战2.0</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">比赛结果</a></li>
</ul>
</div>
<div class="container-wrapper">
<div id="mobile-toggle">
<a href="#"><span class="glyphicon glyphicon-align-justify" aria-hidden="true"></span></a>
</div>
<div id="left-column">
<div class="sphinxsidebar"><a href="
index.html" class="text-logo">多通道多方会议转录挑战2.0</a>
<div class="sidebar-block">
<div class="sidebar-wrapper">
<div id="main-search">
<form class="form-inline" action="search.html" method="GET" role="form">
<div class="input-group">
<input name="q" type="text" class="form-control" placeholder="Search...">
</div>
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
</div>
<div class="sidebar-block">
<div class="sidebar-toc">
<p class="caption" role="heading"><span class="caption-text">目录:</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="%E7%AE%80%E4%BB%8B.html">简介</a><ul>
<li class="toctree-l2"><a class="reference internal" href="%E7%AE%80%E4%BB%8B.html#id2">竞赛介绍</a></li>
<li class="toctree-l2"><a class="reference internal" href="%E7%AE%80%E4%BB%8B.html#aoe">时间安排(AOE时间)</a></li>
<li class="toctree-l2"><a class="reference internal" href="%E7%AE%80%E4%BB%8B.html#id3">竞赛报名</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E6%95%B0%E6%8D%AE%E9%9B%86.html">数据集</a><ul>
<li class="toctree-l2"><a class="reference internal" href="%E6%95%B0%E6%8D%AE%E9%9B%86.html#id2">数据集概述</a></li>
<li class="toctree-l2"><a class="reference internal" href="%E6%95%B0%E6%8D%AE%E9%9B%86.html#alimeeting">Alimeeting数据集介绍</a></li>
<li class="toctree-l2"><a class="reference internal" href="%E6%95%B0%E6%8D%AE%E9%9B%86.html#id3">获取数据</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html">赛道设置与评估</a><ul>
<li class="toctree-l2"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html#id2">说话人相关的语音识别</a></li>
<li class="toctree-l2"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html#id3">评估方法</a></li>
<li class="toctree-l2"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html#id4">子赛道设置</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E5%9F%BA%E7%BA%BF.html">基线</a><ul>
<li class="toctree-l2"><a class="reference internal" href="%E5%9F%BA%E7%BA%BF.html#id2">基线概述</a></li>
<li class="toctree-l2"><a class="reference internal" href="%E5%9F%BA%E7%BA%BF.html#id3">快速开始</a></li>
<li class="toctree-l2"><a class="reference internal" href="%E5%9F%BA%E7%BA%BF.html#id4">基线结果</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>
</div>
</div>
</div>
</div>
<div id="right-column">
<div role="navigation" aria-label="breadcrumbs navigation">
<ol class="breadcrumb">
<li><a href="index.html">Docs</a></li>
<li>比赛结果</li>
</ol>
</div>
<div class="document clearer body">
<section id="id1">
<h1>比赛结果<a class="headerlink" href="#id1" title="此标题的永久链接"></a></h1>
<p>表中为本次竞赛的最终结果，其中Sub-track1代表限定数据子赛道，Sub-track2代表非限定数据子赛道。表中数据均为cp-CER（%）。由于所有队伍的提交均符合限定数据子赛道的要求，表中的排名为两个字赛道合并后的排名。</p>
<table class="docutils align-default">
<thead>
<tr class="row-odd"><th class="head"><p>排名    </p></th>
<th class="head"><p>队伍名称                                </p></th>
<th class="head"><p>子赛道一    </p></th>
<th class="head"><p>子赛道二    </p></th>
<th class="head"><p>论文    </p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>1</p></td>
<td><p>Ximalaya Speech Team</p></td>
<td><p>11.27</p></td>
<td><p>11.27</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>2</p></td>
<td><p>小马达</p></td>
<td><p>18.64</p></td>
<td><p>18.64</p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>3</p></td>
<td><p>AIzyzx</p></td>
<td><p>22.83</p></td>
<td><p>22.83</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>4</p></td>
<td><p>AsrSpeeder</p></td>
<td><p>/</p></td>
<td><p>23.51</p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>5</p></td>
<td><p>zyxlhz</p></td>
<td><p>24.82</p></td>
<td><p>24.82</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>6</p></td>
<td><p>CMCAI</p></td>
<td><p>26.11</p></td>
<td><p>/</p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>7</p></td>
<td><p>Volcspeech</p></td>
<td><p>34.21</p></td>
<td><p>34.21</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>8</p></td>
<td><p>鉴往知来</p></td>
<td><p>40.14</p></td>
<td><p>40.14</p></td>
<td><p></p></td>
</tr>
<tr class="row-even"><td><p>9</p></td>
<td><p>baseline</p></td>
<td><p>41.55</p></td>
<td><p>41.55</p></td>
<td><p></p></td>
</tr>
<tr class="row-odd"><td><p>10</p></td>
<td><p>DAICT</p></td>
<td><p>41.64</p></td>
<td><p></p></td>
<td><p></p></td>
</tr>
</tbody>
</table>
</section>
</div>
<div class="footer-relations">
<div class="pull-left">
<a class="btn btn-default" href="%E8%A7%84%E5%88%99.html" title="上一章 (use the left arrow)">竞赛规则</a>
</div>
<div class="pull-right">
<a class="btn btn-default" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" title="下一章 (use the right arrow)">组委会</a>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="clearfix"></div>
</div>
<div class="related" role="navigation" aria-label="related navigation">
<h3>导航</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="总索引"
>索引</a></li>
<li class="right" >
<a href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" title="组委会"
>下一页</a> |</li>
<li class="right" >
<a href="%E8%A7%84%E5%88%99.html" title="竞赛规则"
>上一页</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">多通道多方会议转录挑战2.0</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">比赛结果</a></li>
</ul>
</div>
<script type="text/javascript">
$("#mobile-toggle a").click(function () {
$("#left-column").toggle();
});
</script>
<script type="text/javascript" src="_static/js/bootstrap.js"></script>
<div class="footer">
&copy; Copyright 2023, Speech Lab, Alibaba Group; ASLP Group, Northwestern Polytechnical University. Created using <a href="http://sphinx.pocoo.org/">Sphinx</a>.
</div>
</body>
</html>

1
docs/m2met2_cn/_build/html/简介.html
View File

@ -102,6 +102,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>

9
docs/m2met2_cn/_build/html/组委会.html
View File

@ -28,7 +28,7 @@
<link rel="index" title="索引" href="genindex.html" />
<link rel="search" title="搜索" href="search.html" />
<link rel="next" title="联系方式" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html" />
<link rel="prev" title="竞赛规则" href="%E8%A7%84%E5%88%99.html" />
<link rel="prev" title="比赛结果" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html" />
@ -43,7 +43,7 @@
<a href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html" title="联系方式"
accesskey="N">下一页</a> |</li>
<li class="right" >
<a href="%E8%A7%84%E5%88%99.html" title="竞赛规则"
<a href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html" title="比赛结果"
accesskey="P">上一页</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">多通道多方会议转录挑战2.0</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">组委会</a></li>
@ -101,6 +101,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>
@ -164,7 +165,7 @@
<div class="footer-relations">
<div class="pull-left">
<a class="btn btn-default" href="%E8%A7%84%E5%88%99.html" title="上一章 (use the left arrow)">竞赛规则</a>
<a class="btn btn-default" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html" title="上一章 (use the left arrow)">比赛结果</a>
</div>
<div class="pull-right">
@ -186,7 +187,7 @@
<a href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html" title="联系方式"
>下一页</a> |</li>
<li class="right" >
<a href="%E8%A7%84%E5%88%99.html" title="竞赛规则"
<a href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html" title="比赛结果"
>上一页</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">多通道多方会议转录挑战2.0</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">组委会</a></li>

1
docs/m2met2_cn/_build/html/联系方式.html
View File

@ -97,6 +97,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">联系方式</a></li>
</ul>

9
docs/m2met2_cn/_build/html/规则.html
View File

@ -27,7 +27,7 @@
<script src="_static/translations.js"></script>
<link rel="index" title="索引" href="genindex.html" />
<link rel="search" title="搜索" href="search.html" />
<link rel="next" title="组委会" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" />
<link rel="next" title="比赛结果" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html" />
<link rel="prev" title="基线" href="%E5%9F%BA%E7%BA%BF.html" />
@ -40,7 +40,7 @@
<a href="genindex.html" title="总索引"
accesskey="I">索引</a></li>
<li class="right" >
<a href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" title="组委会"
<a href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html" title="比赛结果"
accesskey="N">下一页</a> |</li>
<li class="right" >
<a href="%E5%9F%BA%E7%BA%BF.html" title="基线"
@ -101,6 +101,7 @@
</ul>
</li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>
@ -146,7 +147,7 @@
</div>
<div class="pull-right">
<a class="btn btn-default" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" title="下一章 (use the right arrow)">组委会</a>
<a class="btn btn-default" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html" title="下一章 (use the right arrow)">比赛结果</a>
</div>
</div>
<div class="clearer"></div>
@ -161,7 +162,7 @@
<a href="genindex.html" title="总索引"
>索引</a></li>
<li class="right" >
<a href="%E7%BB%84%E5%A7%94%E4%BC%9A.html" title="组委会"
<a href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html" title="比赛结果"
>下一页</a> |</li>
<li class="right" >
<a href="%E5%9F%BA%E7%BA%BF.html" title="基线"

1
docs/m2met2_cn/_build/html/赛道设置与评估.html
View File

@ -102,6 +102,7 @@
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E6%AF%94%E8%B5%9B%E7%BB%93%E6%9E%9C.html">比赛结果</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
</ul>

1
docs/m2met2_cn/index.rst
View File

@ -18,5 +18,6 @@ ASRU 2023 多通道多方会议转录挑战 2.0
./赛道设置与评估
./基线
./规则
./比赛结果
./组委会
./联系方式

14
docs/m2met2_cn/比赛结果.md Normal file
View File

@ -0,0 +1,14 @@
# 比赛结果
表中为本次竞赛的最终结果，其中Sub-track1代表限定数据子赛道，Sub-track2代表非限定数据子赛道。表中数据均为cp-CER（%）。由于所有队伍的提交均符合限定数据子赛道的要求，表中的排名为两个字赛道合并后的排名。
| 排名 &nbsp; &nbsp; |队伍名称 &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; | 子赛道一 &nbsp; &nbsp; | 子赛道二 &nbsp; &nbsp; | 论文 &nbsp; &nbsp; |
|------|----------------------|------------|------------|------------------------|
| 1 | Ximalaya Speech Team | 11.27 | 11.27 | |
| 2 | 小马达 | 18.64 | 18.64 | |
| 3 | AIzyzx | 22.83 | 22.83 | |
| 4 | AsrSpeeder | / | 23.51 | |
| 5 | zyxlhz | 24.82 | 24.82 | |
| 6 | CMCAI | 26.11 | / | |
| 7 | Volcspeech | 34.21 | 34.21 | |
| 8 | 鉴往知来 | 40.14 | 40.14 | |
| 9 | baseline | 41.55 | 41.55 | |
| 10 | DAICT | 41.64 | | |

83
egs/alimeeting/sa_asr_deprecated/README.md
View File

@ -1,83 +0,0 @@
# Get Started
Speaker Attributed Automatic Speech Recognition (SA-ASR) is a task proposed to solve "who spoke what". Specifically, the goal of SA-ASR is not only to obtain multi-speaker transcriptions, but also to identify the corresponding speaker for each utterance. The method used in this example is referenced in the paper: [End-to-End Speaker-Attributed ASR with Transformer](https://www.isca-speech.org/archive/pdfs/interspeech_2021/kanda21b_interspeech.pdf).
To run this receipe, first you need to install FunASR and ModelScope. ([installation](https://github.com/alibaba-damo-academy/FunASR#installation))
There are two startup scripts, `run.sh` for training and evaluating on the old eval and test sets, and `run_m2met_2023_infer.sh` for inference on the new test set of the Multi-Channel Multi-Party Meeting Transcription 2.0 ([M2MeT2.0](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)) Challenge.
Before running `run.sh`, you must manually download and unpack the [AliMeeting](http://www.openslr.org/119/) corpus and place it in the `./dataset` directory:
```shell
dataset
|—— Eval_Ali_far
|—— Eval_Ali_near
|—— Test_Ali_far
|—— Test_Ali_near
|—— Train_Ali_far
|—— Train_Ali_near
```
There are 16 stages in `run.sh`:
```shell
stage 1 - 5: Data preparation and processing.
stage 6: Generate speaker profiles (Stage 6 takes a lot of time).
stage 7 - 9: Language model training (Optional).
stage 10 - 11: ASR training (SA-ASR requires loading the pre-trained ASR model).
stage 12: SA-ASR training.
stage 13 - 16: Inference and evaluation.
```
Before running `run_m2met_2023_infer.sh`, you need to place the new test set `Test_2023_Ali_far` (to be released after the challenge starts) in the `./dataset` directory, which contains only raw audios. Then put the given `wav.scp`, `wav_raw.scp`, `segments`, `utt2spk` and `spk2utt` in the `./data/Test_2023_Ali_far` directory.
```shell
data/Test_2023_Ali_far
|—— wav.scp
|—— wav_raw.scp
|—— segments
|—— utt2spk
|—— spk2utt
```
There are 4 stages in `run_m2met_2023_infer.sh`:
```shell
stage 1: Data preparation and processing.
stage 2: Generate speaker profiles for inference.
stage 3: Inference.
stage 4: Generation of SA-ASR results required for final submission.
```
The baseline model is available on [ModelScope](https://www.modelscope.cn/models/damo/speech_saasr_asr-zh-cn-16k-alimeeting/summary).
After generate stats of AliMeeting corpus(stage 10 in `run.sh`), you can set the `infer_with_pretrained_model=true` in `run.sh` to infer with our official baseline model released on ModelScope without training.
# Format of Final Submission
Finally, you need to submit a file called `text_spk_merge` with the following format:
```shell
Meeting_1 text_spk_1_A$text_spk_1_B$text_spk_1_C ...
Meeting_2 text_spk_2_A$text_spk_2_B$text_spk_2_C ...
...
```
Here, text_spk_1_A represents the full transcription of speaker_A of Meeting_1 (merged in chronological order), and $ represents the separator symbol. There's no need to worry about the speaker permutation as the optimal permutation will be computed in the end. For more information, please refer to the results generated after executing the baseline code.
# Baseline Results
The results of the baseline system are as follows. The baseline results include speaker independent character error rate (SI-CER) and concatenated minimum permutation character error rate (cpCER), the former is speaker independent and the latter is speaker dependent. The speaker profile adopts the oracle speaker embedding during training. However, due to the lack of oracle speaker label during evaluation, the speaker profile provided by an additional spectral clustering is used. Meanwhile, the results of using the oracle speaker profile on Eval and Test Set are also provided to show the impact of speaker profile accuracy.
<table>
<tr >
<td rowspan="2"></td>
<td colspan="2">SI-CER(%)</td>
<td colspan="2">cpCER(%)</td>
</tr>
<tr>
<td>Eval</td>
<td>Test</td>
<td>Eval</td>
<td>Test</td>
</tr>
<tr>
<td>oracle profile</td>
<td>32.05</td>
<td>32.70</td>
<td>47.40</td>
<td>52.57</td>
</tr>
<tr>
<td>cluster profile</td>
<td>32.05</td>
<td>32.70</td>
<td>53.76</td>
<td>55.95</td>
</tr>
</table>
# Reference
N. Kanda, G. Ye, Y. Gaur, X. Wang, Z. Meng, Z. Chen, and T. Yoshioka, "End-to-end speaker-attributed ASR with transformer," in Interspeech. ISCA, 2021, pp. 4413–4417.

1483
egs/alimeeting/sa_asr_deprecated/asr_local.sh
View File

File diff suppressed because it is too large Load Diff

591
egs/alimeeting/sa_asr_deprecated/asr_local_m2met_2023_infer.sh
View File

@ -1,591 +0,0 @@
#!/usr/bin/env bash
# Set bash to 'debug' mode, it will exit on :
# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
set -e
set -u
set -o pipefail
log() {
local fname=${BASH_SOURCE[1]##*/}
echo -e "$(date '+%Y-%m-%dT%H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
}
min() {
local a b
a=$1
for b in "$@"; do
if [ "${b}" -le "${a}" ]; then
a="${b}"
fi
done
echo "${a}"
}
SECONDS=0
# General configuration
stage=1 # Processes starts from the specified stage.
stop_stage=10000 # Processes is stopped at the specified stage.
skip_data_prep=false # Skip data preparation stages.
skip_train=false # Skip training stages.
skip_eval=false # Skip decoding and evaluation stages.
skip_upload=true # Skip packing and uploading stages.
ngpu=1 # The number of gpus ("0" uses cpu, otherwise use gpu).
num_nodes=1 # The number of nodes.
nj=16 # The number of parallel jobs.
inference_nj=16 # The number of parallel jobs in decoding.
gpu_inference=false # Whether to perform gpu decoding.
njob_infer=4
dumpdir=dump2 # Directory to dump features.
expdir=exp # Directory to save experiments.
python=python3 # Specify python to execute espnet commands.
device=0
# Data preparation related
local_data_opts= # The options given to local/data.sh.
# Speed perturbation related
speed_perturb_factors= # perturbation factors, e.g. "0.9 1.0 1.1" (separated by space).
# Feature extraction related
feats_type=raw # Feature type (raw or fbank_pitch).
audio_format=flac # Audio format: wav, flac, wav.ark, flac.ark (only in feats_type=raw).
fs=16000 # Sampling rate.
min_wav_duration=0.1 # Minimum duration in second.
max_wav_duration=20 # Maximum duration in second.
# Tokenization related
token_type=bpe # Tokenization type (char or bpe).
nbpe=30 # The number of BPE vocabulary.
bpemode=unigram # Mode of BPE (unigram or bpe).
oov="<unk>" # Out of vocabulary symbol.
blank="<blank>" # CTC blank symbol
sos_eos="<sos/eos>" # sos and eos symbole
bpe_input_sentence_size=100000000 # Size of input sentence for BPE.
bpe_nlsyms= # non-linguistic symbols list, separated by a comma, for BPE
bpe_char_cover=1.0 # character coverage when modeling BPE
# Language model related
use_lm=true # Use language model for ASR decoding.
lm_tag= # Suffix to the result dir for language model training.
lm_exp= # Specify the direcotry path for LM experiment.
# If this option is specified, lm_tag is ignored.
lm_stats_dir= # Specify the direcotry path for LM statistics.
lm_config= # Config for language model training.
lm_args= # Arguments for language model training, e.g., "--max_epoch 10".
# Note that it will overwrite args in lm config.
use_word_lm=false # Whether to use word language model.
num_splits_lm=1 # Number of splitting for lm corpus.
# shellcheck disable=SC2034
word_vocab_size=10000 # Size of word vocabulary.
# ASR model related
asr_tag= # Suffix to the result dir for asr model training.
asr_exp= # Specify the direcotry path for ASR experiment.
# If this option is specified, asr_tag is ignored.
sa_asr_exp=
asr_stats_dir= # Specify the direcotry path for ASR statistics.
asr_config= # Config for asr model training.
sa_asr_config=
asr_args= # Arguments for asr model training, e.g., "--max_epoch 10".
# Note that it will overwrite args in asr config.
feats_normalize=global_mvn # Normalizaton layer type.
num_splits_asr=1 # Number of splitting for lm corpus.
# Decoding related
inference_tag= # Suffix to the result dir for decoding.
inference_config= # Config for decoding.
inference_args= # Arguments for decoding, e.g., "--lm_weight 0.1".
# Note that it will overwrite args in inference config.
sa_asr_inference_tag=
sa_asr_inference_args=
inference_lm=valid.loss.ave.pb # Language modle path for decoding.
inference_asr_model=valid.acc.ave.pb # ASR model path for decoding.
# e.g.
# inference_asr_model=train.loss.best.pth
# inference_asr_model=3epoch.pth
# inference_asr_model=valid.acc.best.pth
# inference_asr_model=valid.loss.ave.pth
inference_sa_asr_model=valid.acc_spk.ave.pb
download_model= # Download a model from Model Zoo and use it for decoding.
# [Task dependent] Set the datadir name created by local/data.sh
train_set= # Name of training set.
valid_set= # Name of validation set used for monitoring/tuning network training.
test_sets= # Names of test sets. Multiple items (e.g., both dev and eval sets) can be specified.
bpe_train_text= # Text file path of bpe training set.
lm_train_text= # Text file path of language model training set.
lm_dev_text= # Text file path of language model development set.
lm_test_text= # Text file path of language model evaluation set.
nlsyms_txt=none # Non-linguistic symbol list if existing.
cleaner=none # Text cleaner.
g2p=none # g2p method (needed if token_type=phn).
lang=zh # The language type of corpus.
score_opts= # The options given to sclite scoring
local_score_opts= # The options given to local/score.sh.
help_message=$(cat << EOF
Usage: $0 --train-set "<train_set_name>" --valid-set "<valid_set_name>" --test_sets "<test_set_names>"
Options:
# General configuration
--stage # Processes starts from the specified stage (default="${stage}").
--stop_stage # Processes is stopped at the specified stage (default="${stop_stage}").
--skip_data_prep # Skip data preparation stages (default="${skip_data_prep}").
--skip_train # Skip training stages (default="${skip_train}").
--skip_eval # Skip decoding and evaluation stages (default="${skip_eval}").
--skip_upload # Skip packing and uploading stages (default="${skip_upload}").
--ngpu # The number of gpus ("0" uses cpu, otherwise use gpu, default="${ngpu}").
--num_nodes # The number of nodes (default="${num_nodes}").
--nj # The number of parallel jobs (default="${nj}").
--inference_nj # The number of parallel jobs in decoding (default="${inference_nj}").
--gpu_inference # Whether to perform gpu decoding (default="${gpu_inference}").
--dumpdir # Directory to dump features (default="${dumpdir}").
--expdir # Directory to save experiments (default="${expdir}").
--python # Specify python to execute espnet commands (default="${python}").
--device # Which GPUs are use for local training (defalut="${device}").
# Data preparation related
--local_data_opts # The options given to local/data.sh (default="${local_data_opts}").
# Speed perturbation related
--speed_perturb_factors # speed perturbation factors, e.g. "0.9 1.0 1.1" (separated by space, default="${speed_perturb_factors}").
# Feature extraction related
--feats_type # Feature type (raw, fbank_pitch or extracted, default="${feats_type}").
--audio_format # Audio format: wav, flac, wav.ark, flac.ark (only in feats_type=raw, default="${audio_format}").
--fs # Sampling rate (default="${fs}").
--min_wav_duration # Minimum duration in second (default="${min_wav_duration}").
--max_wav_duration # Maximum duration in second (default="${max_wav_duration}").
# Tokenization related
--token_type # Tokenization type (char or bpe, default="${token_type}").
--nbpe # The number of BPE vocabulary (default="${nbpe}").
--bpemode # Mode of BPE (unigram or bpe, default="${bpemode}").
--oov # Out of vocabulary symbol (default="${oov}").
--blank # CTC blank symbol (default="${blank}").
--sos_eos # sos and eos symbole (default="${sos_eos}").
--bpe_input_sentence_size # Size of input sentence for BPE (default="${bpe_input_sentence_size}").
--bpe_nlsyms # Non-linguistic symbol list for sentencepiece, separated by a comma. (default="${bpe_nlsyms}").
--bpe_char_cover # Character coverage when modeling BPE (default="${bpe_char_cover}").
# Language model related
--lm_tag # Suffix to the result dir for language model training (default="${lm_tag}").
--lm_exp # Specify the direcotry path for LM experiment.
# If this option is specified, lm_tag is ignored (default="${lm_exp}").
--lm_stats_dir # Specify the direcotry path for LM statistics (default="${lm_stats_dir}").
--lm_config # Config for language model training (default="${lm_config}").
--lm_args # Arguments for language model training (default="${lm_args}").
# e.g., --lm_args "--max_epoch 10"
# Note that it will overwrite args in lm config.
--use_word_lm # Whether to use word language model (default="${use_word_lm}").
--word_vocab_size # Size of word vocabulary (default="${word_vocab_size}").
--num_splits_lm # Number of splitting for lm corpus (default="${num_splits_lm}").
# ASR model related
--asr_tag # Suffix to the result dir for asr model training (default="${asr_tag}").
--asr_exp # Specify the direcotry path for ASR experiment.
# If this option is specified, asr_tag is ignored (default="${asr_exp}").
--asr_stats_dir # Specify the direcotry path for ASR statistics (default="${asr_stats_dir}").
--asr_config # Config for asr model training (default="${asr_config}").
--asr_args # Arguments for asr model training (default="${asr_args}").
# e.g., --asr_args "--max_epoch 10"
# Note that it will overwrite args in asr config.
--feats_normalize # Normalizaton layer type (default="${feats_normalize}").
--num_splits_asr # Number of splitting for lm corpus (default="${num_splits_asr}").
# Decoding related
--inference_tag # Suffix to the result dir for decoding (default="${inference_tag}").
--inference_config # Config for decoding (default="${inference_config}").
--inference_args # Arguments for decoding (default="${inference_args}").
# e.g., --inference_args "--lm_weight 0.1"
# Note that it will overwrite args in inference config.
--inference_lm # Language modle path for decoding (default="${inference_lm}").
--inference_asr_model # ASR model path for decoding (default="${inference_asr_model}").
--download_model # Download a model from Model Zoo and use it for decoding (default="${download_model}").
# [Task dependent] Set the datadir name created by local/data.sh
--train_set # Name of training set (required).
--valid_set # Name of validation set used for monitoring/tuning network training (required).
--test_sets # Names of test sets.
# Multiple items (e.g., both dev and eval sets) can be specified (required).
--bpe_train_text # Text file path of bpe training set.
--lm_train_text # Text file path of language model training set.
--lm_dev_text # Text file path of language model development set (default="${lm_dev_text}").
--lm_test_text # Text file path of language model evaluation set (default="${lm_test_text}").
--nlsyms_txt # Non-linguistic symbol list if existing (default="${nlsyms_txt}").
--cleaner # Text cleaner (default="${cleaner}").
--g2p # g2p method (default="${g2p}").
--lang # The language type of corpus (default=${lang}).
--score_opts # The options given to sclite scoring (default="{score_opts}").
--local_score_opts # The options given to local/score.sh (default="{local_score_opts}").
EOF
)
log "$0 $*"
# Save command line args for logging (they will be lost after utils/parse_options.sh)
run_args=$(python -m funasr.utils.cli_utils $0 "$@")
. utils/parse_options.sh
if [ $# -ne 0 ]; then
log "${help_message}"
log "Error: No positional arguments are required."
exit 2
fi
. ./path.sh
# Check required arguments
[ -z "${train_set}" ] && { log "${help_message}"; log "Error: --train_set is required"; exit 2; };
[ -z "${valid_set}" ] && { log "${help_message}"; log "Error: --valid_set is required"; exit 2; };
[ -z "${test_sets}" ] && { log "${help_message}"; log "Error: --test_sets is required"; exit 2; };
# Check feature type
if [ "${feats_type}" = raw ]; then
data_feats=${dumpdir}/raw
elif [ "${feats_type}" = fbank_pitch ]; then
data_feats=${dumpdir}/fbank_pitch
elif [ "${feats_type}" = fbank ]; then
data_feats=${dumpdir}/fbank
elif [ "${feats_type}" == extracted ]; then
data_feats=${dumpdir}/extracted
else
log "${help_message}"
log "Error: not supported: --feats_type ${feats_type}"
exit 2
fi
# Use the same text as ASR for bpe training if not specified.
[ -z "${bpe_train_text}" ] && bpe_train_text="${data_feats}/${train_set}/text"
# Use the same text as ASR for lm training if not specified.
[ -z "${lm_train_text}" ] && lm_train_text="${data_feats}/${train_set}/text"
# Use the same text as ASR for lm training if not specified.
[ -z "${lm_dev_text}" ] && lm_dev_text="${data_feats}/${valid_set}/text"
# Use the text of the 1st evaldir if lm_test is not specified
[ -z "${lm_test_text}" ] && lm_test_text="${data_feats}/${test_sets%% *}/text"
# Check tokenization type
if [ "${lang}" != noinfo ]; then
token_listdir=data/${lang}_token_list
else
token_listdir=data/token_list
fi
bpedir="${token_listdir}/bpe_${bpemode}${nbpe}"
bpeprefix="${bpedir}"/bpe
bpemodel="${bpeprefix}".model
bpetoken_list="${bpedir}"/tokens.txt
chartoken_list="${token_listdir}"/char/tokens.txt
# NOTE: keep for future development.
# shellcheck disable=SC2034
wordtoken_list="${token_listdir}"/word/tokens.txt
if [ "${token_type}" = bpe ]; then
token_list="${bpetoken_list}"
elif [ "${token_type}" = char ]; then
token_list="${chartoken_list}"
bpemodel=none
elif [ "${token_type}" = word ]; then
token_list="${wordtoken_list}"
bpemodel=none
else
log "Error: not supported --token_type '${token_type}'"
exit 2
fi
if ${use_word_lm}; then
log "Error: Word LM is not supported yet"
exit 2
lm_token_list="${wordtoken_list}"
lm_token_type=word
else
lm_token_list="${token_list}"
lm_token_type="${token_type}"
fi
# Set tag for naming of model directory
if [ -z "${asr_tag}" ]; then
if [ -n "${asr_config}" ]; then
asr_tag="$(basename "${asr_config}" .yaml)_${feats_type}"
else
asr_tag="train_${feats_type}"
fi
if [ "${lang}" != noinfo ]; then
asr_tag+="_${lang}_${token_type}"
else
asr_tag+="_${token_type}"
fi
if [ "${token_type}" = bpe ]; then
asr_tag+="${nbpe}"
fi
# Add overwritten arg's info
if [ -n "${asr_args}" ]; then
asr_tag+="$(echo "${asr_args}" | sed -e "s/--/\_/g" -e "s/[ |=/]//g")"
fi
if [ -n "${speed_perturb_factors}" ]; then
asr_tag+="_sp"
fi
fi
if [ -z "${lm_tag}" ]; then
if [ -n "${lm_config}" ]; then
lm_tag="$(basename "${lm_config}" .yaml)"
else
lm_tag="train"
fi
if [ "${lang}" != noinfo ]; then
lm_tag+="_${lang}_${lm_token_type}"
else
lm_tag+="_${lm_token_type}"
fi
if [ "${lm_token_type}" = bpe ]; then
lm_tag+="${nbpe}"
fi
# Add overwritten arg's info
if [ -n "${lm_args}" ]; then
lm_tag+="$(echo "${lm_args}" | sed -e "s/--/\_/g" -e "s/[ |=/]//g")"
fi
fi
# The directory used for collect-stats mode
if [ -z "${asr_stats_dir}" ]; then
if [ "${lang}" != noinfo ]; then
asr_stats_dir="${expdir}/asr_stats_${feats_type}_${lang}_${token_type}"
else
asr_stats_dir="${expdir}/asr_stats_${feats_type}_${token_type}"
fi
if [ "${token_type}" = bpe ]; then
asr_stats_dir+="${nbpe}"
fi
if [ -n "${speed_perturb_factors}" ]; then
asr_stats_dir+="_sp"
fi
fi
if [ -z "${lm_stats_dir}" ]; then
if [ "${lang}" != noinfo ]; then
lm_stats_dir="${expdir}/lm_stats_${lang}_${lm_token_type}"
else
lm_stats_dir="${expdir}/lm_stats_${lm_token_type}"
fi
if [ "${lm_token_type}" = bpe ]; then
lm_stats_dir+="${nbpe}"
fi
fi
# The directory used for training commands
if [ -z "${asr_exp}" ]; then
asr_exp="${expdir}/asr_${asr_tag}"
fi
if [ -z "${lm_exp}" ]; then
lm_exp="${expdir}/lm_${lm_tag}"
fi
if [ -z "${inference_tag}" ]; then
if [ -n "${inference_config}" ]; then
inference_tag="$(basename "${inference_config}" .yaml)"
else
inference_tag=inference
fi
# Add overwritten arg's info
if [ -n "${inference_args}" ]; then
inference_tag+="$(echo "${inference_args}" | sed -e "s/--/\_/g" -e "s/[ |=]//g")"
fi
if "${use_lm}"; then
inference_tag+="_lm_$(basename "${lm_exp}")_$(echo "${inference_lm}" | sed -e "s/\//_/g" -e "s/\.[^.]*$//g")"
fi
inference_tag+="_asr_model_$(echo "${inference_asr_model}" | sed -e "s/\//_/g" -e "s/\.[^.]*$//g")"
fi
if [ -z "${sa_asr_inference_tag}" ]; then
if [ -n "${inference_config}" ]; then
sa_asr_inference_tag="$(basename "${inference_config}" .yaml)"
else
sa_asr_inference_tag=sa_asr_inference
fi
# Add overwritten arg's info
if [ -n "${sa_asr_inference_args}" ]; then
sa_asr_inference_tag+="$(echo "${sa_asr_inference_args}" | sed -e "s/--/\_/g" -e "s/[ |=]//g")"
fi
if "${use_lm}"; then
sa_asr_inference_tag+="_lm_$(basename "${lm_exp}")_$(echo "${inference_lm}" | sed -e "s/\//_/g" -e "s/\.[^.]*$//g")"
fi
sa_asr_inference_tag+="_asr_model_$(echo "${inference_sa_asr_model}" | sed -e "s/\//_/g" -e "s/\.[^.]*$//g")"
fi
train_cmd="run.pl"
cuda_cmd="run.pl"
decode_cmd="run.pl"
# ========================== Main stages start from here. ==========================
if ! "${skip_data_prep}"; then
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
if [ "${feats_type}" = raw ]; then
log "Stage 1: Format wav.scp: data/ -> ${data_feats}"
# ====== Recreating "wav.scp" ======
# Kaldi-wav.scp, which can describe the file path with unix-pipe, like "cat /some/path |",
# shouldn't be used in training process.
# "format_wav_scp.sh" dumps such pipe-style-wav to real audio file
# and it can also change the audio-format and sampling rate.
# If nothing is need, then format_wav_scp.sh does nothing:
# i.e. the input file format and rate is same as the output.
for dset in "${test_sets}" ; do
_suf=""
local/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"
rm -f ${data_feats}${_suf}/${dset}/{segments,wav.scp,reco2file_and_channel,reco2dur}
_opts=
if [ -e data/"${dset}"/segments ]; then
# "segments" is used for splitting wav files which are written in "wav".scp
# into utterances. The file format of segments:
# <segment_id> <record_id> <start_time> <end_time>
# "e.g. call-861225-A-0050-0065 call-861225-A 5.0 6.5"
# Where the time is written in seconds.
_opts+="--segments data/${dset}/segments "
fi
# shellcheck disable=SC2086
local/format_wav_scp.sh --nj "${nj}" --cmd "${train_cmd}" \
--audio-format "${audio_format}" --fs "${fs}" ${_opts} \
"data/${dset}/wav.scp" "${data_feats}${_suf}/${dset}"
echo "${feats_type}" > "${data_feats}${_suf}/${dset}/feats_type"
done
else
log "Error: not supported: --feats_type ${feats_type}"
exit 2
fi
fi
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
log "Stage 2: Generate speaker profile by spectral-cluster"
mkdir -p "profile_log"
for dset in "${test_sets}"; do
# generate cluster_profile with spectral-cluster directly (for infering and without oracle information)
python local/gen_cluster_profile_infer.py "${data_feats}/${dset}" "data/${dset}" 0.996 0.815 &> "profile_log/gen_cluster_profile_infer_${dset}.log"
log "Successfully generate cluster profile for ${dset} (${data_feats}/${dset}/cluster_profile_infer.scp)"
done
fi
else
log "Skip the stages for data preparation"
fi
# ========================== Data preparation is done here. ==========================
if ! "${skip_eval}"; then
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
log "Stage 3: Decoding SA-ASR (cluster profile): training_dir=${sa_asr_exp}"
if ${gpu_inference}; then
_cmd="${cuda_cmd}"
inference_nj=$[${ngpu}*${njob_infer}]
_ngpu=1
else
_cmd="${decode_cmd}"
inference_nj=$njob_infer
_ngpu=0
fi
_opts=
if [ -n "${inference_config}" ]; then
_opts+="--config ${inference_config} "
fi
if "${use_lm}"; then
if "${use_word_lm}"; then
_opts+="--word_lm_train_config ${lm_exp}/config.yaml "
_opts+="--word_lm_file ${lm_exp}/${inference_lm} "
else
_opts+="--lm_train_config ${lm_exp}/config.yaml "
_opts+="--lm_file ${lm_exp}/${inference_lm} "
fi
fi
# 2. Generate run.sh
log "Generate '${sa_asr_exp}/${sa_asr_inference_tag}.cluster/run.sh'. You can resume the process from stage 17 using this script"
mkdir -p "${sa_asr_exp}/${sa_asr_inference_tag}.cluster"; echo "${run_args} --stage 17 \"\$@\"; exit \$?" > "${sa_asr_exp}/${sa_asr_inference_tag}.cluster/run.sh"; chmod +x "${sa_asr_exp}/${sa_asr_inference_tag}.cluster/run.sh"
for dset in ${test_sets}; do
_data="${data_feats}/${dset}"
_dir="${sa_asr_exp}/${sa_asr_inference_tag}.cluster/${dset}"
_logdir="${_dir}/logdir"
mkdir -p "${_logdir}"
_feats_type="$(<${_data}/feats_type)"
if [ "${_feats_type}" = raw ]; then
_scp=wav.scp
if [[ "${audio_format}" == *ark* ]]; then
_type=kaldi_ark
else
_type=sound
fi
else
_scp=feats.scp
_type=kaldi_ark
fi
# 1. Split the key file
key_file=${_data}/${_scp}
split_scps=""
_nj=$(min "${inference_nj}" "$(<${key_file} wc -l)")
for n in $(seq "${_nj}"); do
split_scps+=" ${_logdir}/keys.${n}.scp"
done
# shellcheck disable=SC2086
utils/split_scp.pl "${key_file}" ${split_scps}
# 2. Submit decoding jobs
log "Decoding started... log: '${_logdir}/sa_asr_inference.*.log'"
# shellcheck disable=SC2086
${_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
python -m funasr.bin.asr_inference_launch \
--batch_size 1 \
--mc True \
--nbest 1 \
--ngpu "${_ngpu}" \
--njob ${njob_infer} \
--gpuid_list ${device} \
--data_path_and_name_and_type "${_data}/${_scp},speech,${_type}" \
--data_path_and_name_and_type "${_data}/cluster_profile_infer.scp,profile,npy" \
--key_file "${_logdir}"/keys.JOB.scp \
--allow_variable_data_keys true \
--asr_train_config "${sa_asr_exp}"/config.yaml \
--asr_model_file "${sa_asr_exp}"/"${inference_sa_asr_model}" \
--output_dir "${_logdir}"/output.JOB \
--mode sa_asr \
${_opts}
# 3. Concatenates the output files from each jobs
for f in token token_int score text text_id; do
for i in $(seq "${_nj}"); do
cat "${_logdir}/output.${i}/1best_recog/${f}"
done | LC_ALL=C sort -k1 >"${_dir}/${f}"
done
done
fi
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
log "Stage 4: Generate SA-ASR results (cluster profile)"
for dset in ${test_sets}; do
_dir="${sa_asr_exp}/${sa_asr_inference_tag}.cluster/${dset}"
python local/process_text_spk_merge.py ${_dir}
done
fi
else
log "Skip the evaluation stages"
fi
log "Successfully finished. [elapsed=${SECONDS}s]"

6
egs/alimeeting/sa_asr_deprecated/conf/decode_asr_rnn.yaml
View File

@ -1,6 +0,0 @@
beam_size: 20
penalty: 0.0
maxlenratio: 0.0
minlenratio: 0.0
ctc_weight: 0.6
lm_weight: 0.3

88
egs/alimeeting/sa_asr_deprecated/conf/train_asr_conformer.yaml
View File

@ -1,88 +0,0 @@
# network architecture
frontend: default
frontend_conf:
n_fft: 400
win_length: 400
hop_length: 160
use_channel: 0
# encoder related
encoder: conformer
encoder_conf:
output_size: 256 # dimension of attention
attention_heads: 4
linear_units: 2048 # the number of units of position-wise feed forward
num_blocks: 12 # the number of encoder blocks
dropout_rate: 0.1
positional_dropout_rate: 0.1
attention_dropout_rate: 0.0
input_layer: conv2d # encoder architecture type
normalize_before: true
rel_pos_type: latest
pos_enc_layer_type: rel_pos
selfattention_layer_type: rel_selfattn
activation_type: swish
macaron_style: true
use_cnn_module: true
cnn_module_kernel: 15
# decoder related
decoder: transformer
decoder_conf:
attention_heads: 4
linear_units: 2048
num_blocks: 6
dropout_rate: 0.1
positional_dropout_rate: 0.1
self_attention_dropout_rate: 0.0
src_attention_dropout_rate: 0.0
# ctc related
ctc_conf:
ignore_nan_grad: true
# hybrid CTC/attention
model_conf:
ctc_weight: 0.3
lsm_weight: 0.1 # label smoothing option
length_normalized_loss: false
# minibatch related
batch_type: numel
batch_bins: 10000000 # reduce/increase this number according to your GPU memory
# optimization related
accum_grad: 1
grad_clip: 5
max_epoch: 100
val_scheduler_criterion:
- valid
- acc
best_model_criterion:
- - valid
- acc
- max
keep_nbest_models: 10
optim: adam
optim_conf:
lr: 0.001
scheduler: warmuplr
scheduler_conf:
warmup_steps: 25000
specaug: specaug
specaug_conf:
apply_time_warp: true
time_warp_window: 5
time_warp_mode: bicubic
apply_freq_mask: true
freq_mask_width_range:
- 0
- 30
num_freq_mask: 2
apply_time_mask: true
time_mask_width_range:
- 0
- 40
num_time_mask: 2

115
egs/alimeeting/sa_asr_deprecated/conf/train_sa_asr_conformer.yaml
View File

@ -1,115 +0,0 @@
# network architecture
frontend: default
frontend_conf:
n_fft: 400
win_length: 400
hop_length: 160
use_channel: 0
# encoder related
asr_encoder: conformer
asr_encoder_conf:
output_size: 256 # dimension of attention
attention_heads: 4
linear_units: 2048 # the number of units of position-wise feed forward
num_blocks: 12 # the number of encoder blocks
dropout_rate: 0.1
positional_dropout_rate: 0.1
attention_dropout_rate: 0.0
input_layer: conv2d # encoder architecture type
normalize_before: true
pos_enc_layer_type: rel_pos
selfattention_layer_type: rel_selfattn
activation_type: swish
macaron_style: true
use_cnn_module: true
cnn_module_kernel: 15
spk_encoder: resnet34_diar
spk_encoder_conf:
use_head_conv: true
batchnorm_momentum: 0.5
use_head_maxpool: false
num_nodes_pooling_layer: 256
layers_in_block:
- 3
- 4
- 6
- 3
filters_in_block:
- 32
- 64
- 128
- 256
pooling_type: statistic
num_nodes_resnet1: 256
num_nodes_last_layer: 256
# decoder related
decoder: sa_decoder
decoder_conf:
attention_heads: 4
linear_units: 2048
asr_num_blocks: 6
spk_num_blocks: 3
dropout_rate: 0.1
positional_dropout_rate: 0.1
self_attention_dropout_rate: 0.0
src_attention_dropout_rate: 0.0
# hybrid CTC/attention
model_conf:
spk_weight: 0.5
ctc_weight: 0.3
lsm_weight: 0.1 # label smoothing option
length_normalized_loss: false
ctc_conf:
ignore_nan_grad: true
# minibatch related
batch_type: numel
batch_bins: 10000000
# optimization related
accum_grad: 1
grad_clip: 5
max_epoch: 60
val_scheduler_criterion:
- valid
- loss
best_model_criterion:
- - valid
- acc
- max
- - valid
- acc_spk
- max
- - valid
- loss
- min
keep_nbest_models: 10
optim: adam
optim_conf:
lr: 0.0005
scheduler: warmuplr
scheduler_conf:
warmup_steps: 8000
specaug: specaug
specaug_conf:
apply_time_warp: true
time_warp_window: 5
time_warp_mode: bicubic
apply_freq_mask: true
freq_mask_width_range:
- 0
- 30
num_freq_mask: 2
apply_time_mask: true
time_mask_width_range:
- 0
- 40
num_time_mask: 2

1
egs/alimeeting/sa_asr_deprecated/local
View File

@ -1 +0,0 @@
../sa_asr/local/

5
egs/alimeeting/sa_asr_deprecated/path.sh
View File

@ -1,5 +0,0 @@
export FUNASR_DIR=$PWD/../../..
# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
export PYTHONIOENCODING=UTF-8
export PATH=$FUNASR_DIR/funasr/bin:./utils:$PATH

54
egs/alimeeting/sa_asr_deprecated/run.sh
View File

@ -1,54 +0,0 @@
#!/usr/bin/env bash
# Set bash to 'debug' mode, it will exit on :
# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
set -e
set -u
set -o pipefail
ngpu=4
device="0,1,2,3"
stage=1
stop_stage=16
train_set=Train_Ali_far
valid_set=Eval_Ali_far
test_sets="Test_Ali_far"
asr_config=conf/train_asr_conformer.yaml
sa_asr_config=conf/train_sa_asr_conformer.yaml
inference_config=conf/decode_asr_rnn.yaml
infer_with_pretrained_model=false
download_sa_asr_model="damo/speech_saasr_asr-zh-cn-16k-alimeeting"
lm_config=conf/train_lm_transformer.yaml
use_lm=false
use_wordlm=false
./asr_local.sh \
--device ${device} \
--ngpu ${ngpu} \
--stage ${stage} \
--stop_stage ${stop_stage} \
--gpu_inference true \
--njob_infer 4 \
--infer_with_pretrained_model ${infer_with_pretrained_model} \
--download_sa_asr_model $download_sa_asr_model \
--asr_exp exp/asr_train_multispeaker_conformer_raw_zh_char_data_alimeeting \
--sa_asr_exp exp/sa_asr_train_conformer_raw_zh_char_data_alimeeting \
--asr_stats_dir exp/asr_stats_multispeaker_conformer_raw_zh_char_data_alimeeting \
--lm_exp exp/lm_train_multispeaker_transformer_zh_char_data_alimeeting \
--lm_stats_dir exp/lm_stats_multispeaker_zh_char_data_alimeeting \
--lang zh \
--audio_format wav \
--feats_type raw \
--token_type char \
--use_lm ${use_lm} \
--use_word_lm ${use_wordlm} \
--lm_config "${lm_config}" \
--asr_config "${asr_config}" \
--sa_asr_config "${sa_asr_config}" \
--inference_config "${inference_config}" \
--train_set "${train_set}" \
--valid_set "${valid_set}" \
--test_sets "${test_sets}" \
--lm_train_text "data/${train_set}/text" "$@"

50
egs/alimeeting/sa_asr_deprecated/run_m2met_2023_infer.sh
View File

@ -1,50 +0,0 @@
#!/usr/bin/env bash
# Set bash to 'debug' mode, it will exit on :
# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
set -e
set -u
set -o pipefail
ngpu=4
device="0,1,2,3"
stage=1
stop_stage=4
train_set=Train_Ali_far
valid_set=Eval_Ali_far
test_sets="Test_2023_Ali_far"
asr_config=conf/train_asr_conformer.yaml
sa_asr_config=conf/train_sa_asr_conformer.yaml
inference_config=conf/decode_asr_rnn.yaml
lm_config=conf/train_lm_transformer.yaml
use_lm=false
use_wordlm=false
./asr_local_m2met_2023_infer.sh \
--device ${device} \
--ngpu ${ngpu} \
--stage ${stage} \
--stop_stage ${stop_stage} \
--gpu_inference true \
--njob_infer 4 \
--asr_exp exp/asr_train_multispeaker_conformer_raw_zh_char_data_alimeeting \
--sa_asr_exp exp/sa_asr_train_conformer_raw_zh_char_data_alimeeting \
--asr_stats_dir exp/asr_stats_multispeaker_conformer_raw_zh_char_data_alimeeting \
--lm_exp exp/lm_train_multispeaker_transformer_zh_char_data_alimeeting \
--lm_stats_dir exp/lm_stats_multispeaker_zh_char_data_alimeeting \
--lang zh \
--audio_format wav \
--feats_type raw \
--token_type char \
--use_lm ${use_lm} \
--use_word_lm ${use_wordlm} \
--lm_config "${lm_config}" \
--asr_config "${asr_config}" \
--sa_asr_config "${sa_asr_config}" \
--inference_config "${inference_config}" \
--train_set "${train_set}" \
--valid_set "${valid_set}" \
--test_sets "${test_sets}" \
--lm_train_text "data/${train_set}/text" "$@"

1
egs/alimeeting/sa_asr_deprecated/utils
View File

@ -1 +0,0 @@
../../aishell/transformer/utils