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

docs

Browse Source
This commit is contained in:
游雁 2023-04-27 21:52:09 +08:00
parent c699b484b1
commit 7ebfaac337
5 changed files with 57 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
egs_modelscope/asr/TEMPLATE/README.md
View File

@ -102,20 +102,20 @@ print(rec_result)
### Inference with multi-thread CPUs or multi GPUs
FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
- Setting parameters in `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `data_dir`: the dataset dir needs to include `wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
- `output_dir`: output dir of the recognition results
- `batch_size`: `64` (Default), batch size of inference on gpu
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
- `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast、normal、offline)
- `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
#### Settings of `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `data_dir`: the dataset dir needs to include `wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
- `output_dir`: output dir of the recognition results
- `batch_size`: `64` (Default), batch size of inference on gpu
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
- `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast、normal、offline)
- `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
- Decode with multi GPUs:
#### Decode with multi GPUs:
```shell
bash infer.sh \
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@ -125,7 +125,7 @@ FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.
--gpu_inference true \
--gpuid_list "0,1"
```
- Decode with multi-thread CPUs:
#### Decode with multi-thread CPUs:
```shell
bash infer.sh \
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@ -135,7 +135,7 @@ FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.
--njob 64
```
- Results
#### Results
The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.

23
egs_modelscope/punctuation/TEMPLATE/README.md
View File

@ -70,17 +70,17 @@ Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/
### Inference with multi-thread CPUs or multi GPUs
FunASR also offer recipes [egs_modelscope/punctuation/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/punctuation/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs. It is an offline recipe and only support offline model.
- Setting parameters in `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `data_dir`: the dataset dir needs to include `punc.txt`
- `output_dir`: output dir of the recognition results
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `punc.pb` (Default), which checkpoint is used to infer
#### Settings of `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `data_dir`: the dataset dir needs to include `punc.txt`
- `output_dir`: output dir of the recognition results
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `punc.pb` (Default), which checkpoint is used to infer
- Decode with multi GPUs:
#### Decode with multi GPUs:
```shell
bash infer.sh \
--model "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch" \
@ -90,7 +90,7 @@ FunASR also offer recipes [egs_modelscope/punctuation/TEMPLATE/infer.sh](https:/
--gpu_inference true \
--gpuid_list "0,1"
```
- Decode with multi-thread CPUs:
#### Decode with multi-thread CPUs:
```shell
bash infer.sh \
--model "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch" \
@ -100,7 +100,6 @@ FunASR also offer recipes [egs_modelscope/punctuation/TEMPLATE/infer.sh](https:/
--njob 1
```
## Finetune with pipeline
### Quick start

24
egs_modelscope/tp/TEMPLATE/README.md
View File

@ -61,18 +61,18 @@ Timestamp pipeline can also be used after ASR pipeline to compose complete ASR f
### Inference with multi-thread CPUs or multi GPUs
FunASR also offer recipes [egs_modelscope/tp/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/tp/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
- Setting parameters in `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `data_dir`: the dataset dir **must** include `wav.scp` and `text.txt`
- `output_dir`: output dir of the recognition results
- `batch_size`: `64` (Default), batch size of inference on gpu
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
#### Settings of `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `data_dir`: the dataset dir **must** include `wav.scp` and `text.txt`
- `output_dir`: output dir of the recognition results
- `batch_size`: `64` (Default), batch size of inference on gpu
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
- Decode with multi GPUs:
#### Decode with multi GPUs:
```shell
bash infer.sh \
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@ -82,7 +82,7 @@ FunASR also offer recipes [egs_modelscope/tp/TEMPLATE/infer.sh](https://github.c
--gpu_inference true \
--gpuid_list "0,1"
```
- Decode with multi-thread CPUs:
#### Decode with multi-thread CPUs:
```shell
bash infer.sh \
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \

24
egs_modelscope/vad/TEMPLATE/README.md
View File

@ -69,18 +69,18 @@ Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/
### Inference with multi-thread CPUs or multi GPUs
FunASR also offer recipes [egs_modelscope/vad/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/vad/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
- Setting parameters in `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `data_dir`: the dataset dir needs to include `wav.scp`
- `output_dir`: output dir of the recognition results
- `batch_size`: `64` (Default), batch size of inference on gpu
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
#### Settings of `infer.sh`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `data_dir`: the dataset dir needs to include `wav.scp`
- `output_dir`: output dir of the recognition results
- `batch_size`: `64` (Default), batch size of inference on gpu
- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
- Decode with multi GPUs:
#### Decode with multi GPUs:
```shell
bash infer.sh \
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@ -90,7 +90,7 @@ FunASR also offer recipes [egs_modelscope/vad/TEMPLATE/infer.sh](https://github.
--gpu_inference true \
--gpuid_list "0,1"
```
- Decode with multi-thread CPUs:
#### Decode with multi-thread CPUs:
```shell
bash infer.sh \
--model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \

9
funasr/runtime/python/websocket/README.md
View File

@ -51,12 +51,17 @@ cd funasr/runtime/python/websocket
pip install -r requirements_client.txt
```
Start client
### Start client
#### Recording from mircrophone
```shell
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
python ws_client.py --host "127.0.0.1" --port 10096 --chunk_size "5,10,5"
```
#### Loadding from wav.scp(kaldi style)
```shell
# --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
python ws_client.py --host "127.0.0.1" --port 10096 --chunk_size "5,10,5" --audio_in "./data/wav.scp"
```
## Acknowledge
1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).