From a96350ff4fe0b53d8544de101817881d6ff105b2 Mon Sep 17 00:00:00 2001
From: yhliang <68215459+yhliang-aslp@users.noreply.github.com>
Date: 星期五, 21 四月 2023 11:46:34 +0800
Subject: [PATCH] Merge pull request #392 from alibaba-damo-academy/main
---
docs/modescope_pipeline/quick_start.md | 25 +++++++++++++++++--------
1 files changed, 17 insertions(+), 8 deletions(-)
diff --git a/docs/modescope_pipeline/quick_start.md b/docs/modescope_pipeline/quick_start.md
index b1614f5..e6a85d9 100644
--- a/docs/modescope_pipeline/quick_start.md
+++ b/docs/modescope_pipeline/quick_start.md
@@ -1,9 +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
@@ -15,10 +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
@@ -34,10 +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
@@ -49,10 +55,11 @@
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
@@ -65,10 +72,11 @@
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
@@ -85,10 +93,11 @@
# 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
+### Speaker Diarization
+#### SOND Model
```python
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
@@ -154,7 +163,7 @@
## Finetune with pipeline
### Speech Recognition
-#### Paraformer model
+#### Paraformer Model
finetune.py
```python
--
Gitblit v1.9.1