mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
docs
This commit is contained in:
游雁
parent
66b502164d
commit
7a0c0f3399
@ -45,7 +45,9 @@ FunASR hopes to build a bridge between academic research and industrial applicat
|
||||
./modescope_pipeline/asr_pipeline.md
|
||||
./modescope_pipeline/vad_pipeline.md
|
||||
./modescope_pipeline/punc_pipeline.md
|
||||
./modescope_pipeline/tp_pipeline.md
|
||||
./modescope_pipeline/sv_pipeline.md
|
||||
./modescope_pipeline/lm_pipeline.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
@ -65,9 +67,6 @@ FunASR hopes to build a bridge between academic research and industrial applicat
|
||||
|
||||
./papers.md
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: API Reference
|
||||
|
||||
|
||||
|
||||
|
||||
@ -1,6 +1,138 @@
|
||||
# Quick Start
|
||||
|
||||
## Inference with pipeline
|
||||
|
||||
### Speech Recognition
|
||||
#### Paraformer model
|
||||
```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)
|
||||
```
|
||||
|
||||
### Voice Activity Detection
|
||||
#### FSMN-VAD
|
||||
```python
|
||||
from modelscope.pipelines import pipeline
|
||||
from modelscope.utils.constant import Tasks
|
||||
from modelscope.utils.logger import get_logger
|
||||
import logging
|
||||
logger = get_logger(log_level=logging.CRITICAL)
|
||||
logger.setLevel(logging.CRITICAL)
|
||||
|
||||
inference_pipeline = pipeline(
|
||||
task=Tasks.voice_activity_detection,
|
||||
model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
|
||||
)
|
||||
|
||||
segments_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav')
|
||||
print(segments_result)
|
||||
```
|
||||
|
||||
### Punctuation Restoration
|
||||
#### CT_Transformer
|
||||
```python
|
||||
from modelscope.pipelines import pipeline
|
||||
from modelscope.utils.constant import Tasks
|
||||
|
||||
inference_pipeline = pipeline(
|
||||
task=Tasks.punctuation,
|
||||
model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
|
||||
)
|
||||
|
||||
rec_result = inference_pipeline(text_in='我们都是木头人不会讲话不会动')
|
||||
print(rec_result)
|
||||
```
|
||||
|
||||
### Timestamp Prediction
|
||||
#### TP-Aligner
|
||||
```python
|
||||
from modelscope.pipelines import pipeline
|
||||
from modelscope.utils.constant import Tasks
|
||||
|
||||
inference_pipeline = pipeline(
|
||||
task=Tasks.speech_timestamp,
|
||||
model='damo/speech_timestamp_prediction-v1-16k-offline',
|
||||
output_dir='./tmp')
|
||||
|
||||
rec_result = inference_pipeline(
|
||||
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_timestamps.wav',
|
||||
text_in='一 个 东 太 平 洋 国 家 为 什 么 跑 到 西 太 平 洋 来 了 呢',)
|
||||
print(rec_result)
|
||||
```
|
||||
|
||||
### Speaker Verification
|
||||
#### X-vector
|
||||
```python
|
||||
from modelscope.pipelines import pipeline
|
||||
from modelscope.utils.constant import Tasks
|
||||
import numpy as np
|
||||
|
||||
inference_sv_pipline = pipeline(
|
||||
task=Tasks.speaker_verification,
|
||||
model='damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch'
|
||||
)
|
||||
|
||||
# embedding extract
|
||||
spk_embedding = inference_sv_pipline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_enroll.wav')["spk_embedding"]
|
||||
|
||||
# speaker verification
|
||||
rec_result = inference_sv_pipline(audio_in=('https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_enroll.wav','https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_same.wav'))
|
||||
print(rec_result["scores"][0])
|
||||
```
|
||||
|
||||
## Finetune with pipeline
|
||||
### Speech Recognition
|
||||
#### Paraformer model
|
||||
|
||||
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" # 模型保存路径
|
||||
params.data_path = "speech_asr_aishell1_trainsets" # 数据路径，可以为modelscope中已上传数据，也可以是本地数据
|
||||
params.dataset_type = "small" # 小数据量设置small，若数据量大于1000小时，请使用large
|
||||
params.batch_bins = 2000 # batch size，如果dataset_type="small"，batch_bins单位为fbank特征帧数，如果dataset_type="large"，batch_bins单位为毫秒，
|
||||
params.max_epoch = 50 # 最大训练轮数
|
||||
params.lr = 0.00005 # 设置学习率
|
||||
|
||||
modelscope_finetune(params)
|
||||
```
|
||||
|
||||
```shell
|
||||
python finetune.py &> log.txt &
|
||||
```
|
||||
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
|
||||
```
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user