From 7a0c0f3399ea0c719657a3caa4a4d0ea10aa9cc8 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 18 四月 2023 17:29:57 +0800
Subject: [PATCH] docs
---
docs/modescope_pipeline/quick_start.md | 134 ++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 133 insertions(+), 1 deletions(-)
diff --git a/docs/modescope_pipeline/quick_start.md b/docs/modescope_pipeline/quick_start.md
index f294ef8..668ec1f 100644
--- a/docs/modescope_pipeline/quick_start.md
+++ b/docs/modescope_pipeline/quick_start.md
@@ -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='鎴戜滑閮芥槸鏈ㄥご浜轰笉浼氳璇濅笉浼氬姩')
+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='涓� 涓� 涓� 澶� 骞� 娲� 鍥� 瀹� 涓� 浠� 涔� 璺� 鍒� 瑗� 澶� 骞� 娲� 鏉� 浜� 鍛�',)
+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" # 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 &
+```
+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
+```
+
--
Gitblit v1.9.1