From d5784e3444ff891b92c681d866f1d527a25cb299 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期日, 23 四月 2023 15:51:59 +0800
Subject: [PATCH] Merge pull request #404 from alibaba-damo-academy/main
---
egs_modelscope/asr/TEMPLATE/README.md | 213 +++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 213 insertions(+), 0 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
new file mode 100644
index 0000000..c645033
--- /dev/null
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -0,0 +1,213 @@
+# Speech Recognition
+
+> **Note**:
+> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take the typic models as examples to demonstrate the usage.
+
+## Inference
+
+### Quick start
+#### [Paraformer Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)
+```
+#### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
+```python
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
+ )
+import soundfile
+speech, sample_rate = soundfile.read("example/asr_example.wav")
+
+param_dict = {"cache": dict(), "is_final": False}
+chunk_stride = 7680# 480ms
+# first chunk, 480ms
+speech_chunk = speech[0:chunk_stride]
+rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
+print(rec_result)
+# next chunk, 480ms
+speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
+rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
+print(rec_result)
+```
+Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
+
+#### [UniASR Model](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
+There are three decoding mode for UniASR model(`fast`銆乣normal`銆乣offline`), for more model detailes, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
+```python
+decoding_model = "fast" # "fast"銆�"normal"銆�"offline"
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825',
+ param_dict={"decoding_model": decoding_model})
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)
+```
+The decoding mode of `fast` and `normal` is fake streaming, which could be used for evaluating of recognition accuracy.
+Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
+#### [RNN-T-online model]()
+Undo
+
+#### API-reference
+##### Define pipeline
+- `task`: `Tasks.auto_speech_recognition`
+- `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
+- `ngpu`: `1` (Default), decoding on GPU. If ngpu=0, decoding on CPU
+- `ncpu`: `1` (Default), sets the number of threads used for intraop parallelism on CPU
+- `output_dir`: `None` (Default), the output path of results if set
+- `batch_size`: `1` (Default), batch size when decoding
+##### Infer pipeline
+- `audio_in`: the input to decode, which could be:
+ - wav_path, `e.g.`: asr_example.wav,
+ - pcm_path, `e.g.`: asr_example.pcm,
+ - audio bytes stream, `e.g.`: bytes data from a microphone
+ - audio sample point锛宍e.g.`: `audio, rate = soundfile.read("asr_example_zh.wav")`, the dtype is numpy.ndarray or torch.Tensor
+ - wav.scp, kaldi style wav list (`wav_id \t wav_path``), `e.g.`:
+ ```text
+ asr_example1 ./audios/asr_example1.wav
+ asr_example2 ./audios/asr_example2.wav
+ ```
+ In this case of `wav.scp` input, `output_dir` must be set to save the output results
+- `audio_fs`: audio sampling rate, only set when audio_in is pcm audio
+- `output_dir`: None (Default), the output path of results if set
+
+### Inference with multi-thread CPUs or multi GPUs
+FunASR also offer recipes [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 `${data_dir}/text` is also exists, CER will be computed
+ - `output_dir`: output dir of the recognition results
+ - `batch_size`: `64` (Default), batch size of inference on gpu
+ - `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
+ - `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
+ - `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
+ - `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
+ - `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
+
+- Decode with multi GPUs:
+```shell
+ bash infer.sh \
+ --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+ --data_dir "./data/test" \
+ --output_dir "./results" \
+ --batch_size 64 \
+ --gpu_inference true \
+ --gpuid_list "0,1"
+```
+- Decode with multi-thread CPUs:
+```shell
+ bash infer.sh \
+ --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+ --data_dir "./data/test" \
+ --output_dir "./results" \
+ --gpu_inference false \
+ --njob 64
+```
+
+- Results
+
+The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
+
+If you decode the SpeechIO test sets, you can use textnorm with `stage`=3, and `DETAILS.txt`, `RESULTS.txt` record the results and CER after text normalization.
+
+
+## Finetune with pipeline
+
+### Quick start
+[finetune.py](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/finetune.py)
+```python
+import os
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+from modelscope.msdatasets.audio.asr_dataset import ASRDataset
+
+def modelscope_finetune(params):
+ if not os.path.exists(params.output_dir):
+ os.makedirs(params.output_dir, exist_ok=True)
+ # dataset split ["train", "validation"]
+ ds_dict = ASRDataset.load(params.data_path, namespace='speech_asr')
+ kwargs = dict(
+ model=params.model,
+ data_dir=ds_dict,
+ dataset_type=params.dataset_type,
+ work_dir=params.output_dir,
+ batch_bins=params.batch_bins,
+ max_epoch=params.max_epoch,
+ lr=params.lr)
+ trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
+ trainer.train()
+
+
+if __name__ == '__main__':
+ from funasr.utils.modelscope_param import modelscope_args
+ params = modelscope_args(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+ params.output_dir = "./checkpoint" # 妯″瀷淇濆瓨璺緞
+ params.data_path = "speech_asr_aishell1_trainsets" # 鏁版嵁璺緞锛屽彲浠ヤ负modelscope涓凡涓婁紶鏁版嵁锛屼篃鍙互鏄湰鍦版暟鎹�
+ params.dataset_type = "small" # 灏忔暟鎹噺璁剧疆small锛岃嫢鏁版嵁閲忓ぇ浜�1000灏忔椂锛岃浣跨敤large
+ params.batch_bins = 2000 # batch size锛屽鏋渄ataset_type="small"锛宐atch_bins鍗曚綅涓篺bank鐗瑰緛甯ф暟锛屽鏋渄ataset_type="large"锛宐atch_bins鍗曚綅涓烘绉掞紝
+ params.max_epoch = 50 # 鏈�澶ц缁冭疆鏁�
+ params.lr = 0.00005 # 璁剧疆瀛︿範鐜�
+
+ modelscope_finetune(params)
+```
+
+```shell
+python finetune.py &> log.txt &
+```
+
+### Finetune with your data
+
+- Modify finetune training related parameters in [finetune.py](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/finetune.py)
+ - `output_dir`: result dir
+ - `data_dir`: the dataset dir needs to include files: `train/wav.scp`, `train/text`; `validation/wav.scp`, `validation/text`
+ - `dataset_type`: for dataset larger than 1000 hours, set as `large`, otherwise set as `small`
+ - `batch_bins`: batch size. For dataset_type is `small`, `batch_bins` indicates the feature frames. For dataset_type is `large`, `batch_bins` indicates the duration in ms
+ - `max_epoch`: number of training epoch
+ - `lr`: learning rate
+
+- Then you can run the pipeline to finetune with:
+```shell
+python finetune.py
+```
+If you want finetune with multi-GPUs, you could:
+```shell
+CUDA_VISIBLE_DEVICES=1,2 python -m torch.distributed.launch --nproc_per_node 2 finetune.py > log.txt 2>&1
+```
+## Inference with your finetuned model
+
+- Setting parameters in [infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) is the same with [docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/egs_modelscope/asr/TEMPLATE#inference-with-multi-thread-cpus-or-multi-gpus), `model` is the model name from modelscope, which you finetuned.
+
+- Decode with multi GPUs:
+```shell
+ bash infer.sh \
+ --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+ --data_dir "./data/test" \
+ --output_dir "./results" \
+ --batch_size 64 \
+ --gpu_inference true \
+ --gpuid_list "0,1" \
+ --checkpoint_dir "./checkpoint" \
+ --checkpoint_name "valid.cer_ctc.ave.pb"
+```
+- Decode with multi-thread CPUs:
+```shell
+ bash infer.sh \
+ --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+ --data_dir "./data/test" \
+ --output_dir "./results" \
+ --gpu_inference false \
+ --njob 64 \
+ --checkpoint_dir "./checkpoint" \
+ --checkpoint_name "valid.cer_ctc.ave.pb"
+```
\ No newline at end of file
--
Gitblit v1.9.1