From 3cd3473bf7a3b41484baa86d9092248d78e7af39 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 21 四月 2023 17:17:37 +0800
Subject: [PATCH] docs
---
docs/modescope_pipeline/quick_start.md | 96 ++++++++++++++++++++++++++++++++++++++++++++----
1 files changed, 88 insertions(+), 8 deletions(-)
diff --git a/docs/modescope_pipeline/quick_start.md b/docs/modescope_pipeline/quick_start.md
index 668ec1f..8272d3b 100644
--- a/docs/modescope_pipeline/quick_start.md
+++ b/docs/modescope_pipeline/quick_start.md
@@ -1,8 +1,13 @@
+# Quick Start
+
+> **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 typic model as example to demonstrate the usage.
+
## Inference with pipeline
### Speech Recognition
-#### Paraformer model
+#### Paraformer Model
```python
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
@@ -14,10 +19,11 @@
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)
+# {'text': '娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�'}
```
### Voice Activity Detection
-#### FSMN-VAD
+#### FSMN-VAD Model
```python
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
@@ -33,10 +39,11 @@
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)
+# {'text': [[70, 2340], [2620, 6200], [6480, 23670], [23950, 26250], [26780, 28990], [29950, 31430], [31750, 37600], [38210, 46900], [47310, 49630], [49910, 56460], [56740, 59540], [59820, 70450]]}
```
### Punctuation Restoration
-#### CT_Transformer
+#### CT_Transformer Model
```python
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
@@ -48,27 +55,28 @@
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)
+# {'text': '鎴戜滑閮芥槸鏈ㄥご浜猴紝涓嶄細璁茶瘽锛屼笉浼氬姩銆�'}
```
### Timestamp Prediction
-#### TP-Aligner
+#### TP-Aligner Model
```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')
+ model='damo/speech_timestamp_prediction-v1-16k-offline',)
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)
+# {'text': '<sil> 0.000 0.380;涓� 0.380 0.560;涓� 0.560 0.800;涓� 0.800 0.980;澶� 0.980 1.140;骞� 1.140 1.260;娲� 1.260 1.440;鍥� 1.440 1.680;瀹� 1.680 1.920;<sil> 1.920 2.040;涓� 2.040 2.200;浠� 2.200 2.320;涔� 2.320 2.500;璺� 2.500 2.680;鍒� 2.680 2.860;瑗� 2.860 3.040;澶� 3.040 3.200;骞� 3.200 3.380;娲� 3.380 3.500;鏉� 3.500 3.640;浜� 3.640 3.800;鍛� 3.800 4.150;<sil> 4.150 4.440;', 'timestamp': [[380, 560], [560, 800], [800, 980], [980, 1140], [1140, 1260], [1260, 1440], [1440, 1680], [1680, 1920], [2040, 2200], [2200, 2320], [2320, 2500], [2500, 2680], [2680, 2860], [2860, 3040], [3040, 3200], [3200, 3380], [3380, 3500], [3500, 3640], [3640, 3800], [3800, 4150]]}
```
### Speaker Verification
-#### X-vector
+#### X-vector Model
```python
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
@@ -85,11 +93,79 @@
# 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])
+# 0.8540499500025098
+```
+
+### Speaker Diarization
+#### SOND Model
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_diar_pipline = pipeline(
+ mode="sond_demo",
+ num_workers=0,
+ task=Tasks.speaker_diarization,
+ diar_model_config="sond.yaml",
+ model='damo/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch',
+ model_revision="v1.0.3",
+ sv_model="damo/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch",
+ sv_model_revision="v1.0.0",
+)
+
+audio_list=[
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/record.wav",
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_A.wav",
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B.wav",
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B1.wav"
+]
+
+results = inference_diar_pipline(audio_in=audio_list)
+print(results)
+# {'text': 'spk1 [(0.8, 1.84), (2.8, 6.16), (7.04, 10.64), (12.08, 12.8), (14.24, 15.6)]\nspk2 [(0.0, 1.12), (1.68, 3.2), (4.48, 7.12), (8.48, 9.04), (10.56, 14.48), (15.44, 16.0)]'}
+```
+
+### FAQ
+#### How to switch device from GPU to CPU with pipeline
+
+The pipeline defaults to decoding with GPU (`ngpu=1`) when GPU is available. If you want to switch to CPU, you could set `ngpu=0`
+```python
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+ ngpu=0,
+)
+```
+
+#### How to infer from local model path
+Download model to local dir, by modelscope-sdk
+
+```python
+from modelscope.hub.snapshot_download import snapshot_download
+
+local_dir_root = "./models_from_modelscope"
+model_dir = snapshot_download('damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch', cache_dir=local_dir_root)
+```
+
+Or download model to local dir, by git lfs
+```shell
+git lfs install
+# git clone https://www.modelscope.cn/<namespace>/<model-name>.git
+git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git
+```
+
+Infer with local model path
+```python
+local_dir_root = "./models_from_modelscope/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model=local_dir_root,
+)
```
## Finetune with pipeline
### Speech Recognition
-#### Paraformer model
+#### Paraformer Model
finetune.py
```python
@@ -131,6 +207,10 @@
```shell
python finetune.py &> log.txt &
```
+
+### FAQ
+### Multi GPUs training and distributed training
+
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