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

tutorial

Browse Source
This commit is contained in:
游雁 2024-03-21 17:04:03 +08:00
parent 123c92dd25
commit 86fb406bb7
3 changed files with 36 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
docs/tutorial/README_zh.md
View File

@ -137,6 +137,9 @@ torchrun --nnodes 2 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --mast
#### 准备数据 #### 准备数据
`jsonl`格式可以参考（[例子](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)）。
可以用指令 `scp2jsonl` 从wav.scp与text.txt生成。wav.scp与text.txt准备过程如下：
`train_text.txt` `train_text.txt`
左边为数据唯一ID，需与`train_wav.scp`中的`ID`一一对应 左边为数据唯一ID，需与`train_wav.scp`中的`ID`一一对应
@ -160,6 +163,15 @@ BAC009S0916W0489 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test
ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav
``` ```
`生成指令`
```shell
# generate train.jsonl and val.jsonl from wav.scp and text.txt
scp2jsonl \
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="../../../data/list/train.jsonl"
```
#### 查看训练日志 #### 查看训练日志

12
examples/README_zh.md
View File

@ -137,6 +137,9 @@ torchrun --nnodes 2 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --mast
#### 准备数据 #### 准备数据
`jsonl`格式可以参考（[例子](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)）。
可以用指令 `scp2jsonl` 从wav.scp与text.txt生成。wav.scp与text.txt准备过程如下：
`train_text.txt` `train_text.txt`
左边为数据唯一ID，需与`train_wav.scp`中的`ID`一一对应 左边为数据唯一ID，需与`train_wav.scp`中的`ID`一一对应
@ -160,6 +163,15 @@ BAC009S0916W0489 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test
ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav
``` ```
`生成指令`
```shell
# generate train.jsonl and val.jsonl from wav.scp and text.txt
scp2jsonl \
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="../../../data/list/train.jsonl"
```
#### 查看训练日志 #### 查看训练日志

12
examples/industrial_data_pretraining/paraformer/README_zh.md
View File

@ -137,6 +137,9 @@ torchrun --nnodes 2 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --mast
#### 准备数据 #### 准备数据
`jsonl`格式可以参考（[例子](https://github.com/alibaba-damo-academy/FunASR/blob/main/data/list)）。
可以用指令 `scp2jsonl` 从wav.scp与text.txt生成。wav.scp与text.txt准备过程如下：
`train_text.txt` `train_text.txt`
左边为数据唯一ID，需与`train_wav.scp`中的`ID`一一对应 左边为数据唯一ID，需与`train_wav.scp`中的`ID`一一对应
@ -160,6 +163,15 @@ BAC009S0916W0489 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test
ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav ID0012W0015 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav
``` ```
`生成指令`
```shell
# generate train.jsonl and val.jsonl from wav.scp and text.txt
scp2jsonl \
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="../../../data/list/train.jsonl"
```
#### 查看训练日志 #### 查看训练日志