From 2e36e738ca39afc8d02f3d11013bd12f937cc874 Mon Sep 17 00:00:00 2001
From: zhaomingwork <61895407+zhaomingwork@users.noreply.github.com>
Date: 星期三, 08 十一月 2023 09:22:06 +0800
Subject: [PATCH] fix bug for h5 hotwords (#1067)
---
egs_modelscope/vad/TEMPLATE/README.md | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/egs_modelscope/vad/TEMPLATE/README.md b/egs_modelscope/vad/TEMPLATE/README.md
index 945f9fa..2651dce 100644
--- a/egs_modelscope/vad/TEMPLATE/README.md
+++ b/egs_modelscope/vad/TEMPLATE/README.md
@@ -1,3 +1,5 @@
+([绠�浣撲腑鏂嘳(./README_zh.md)|English)
+
# Voice Activity Detection
> **Note**:
@@ -22,7 +24,7 @@
#### [FSMN-VAD-online model](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary)
```python
inference_pipeline = pipeline(
- task=Tasks.auto_speech_recognition,
+ task=Tasks.voice_activity_detection,
model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
)
import soundfile
@@ -34,7 +36,7 @@
speech_chunk = speech[0:chunk_stride]
rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
print(rec_result)
-# next chunk, 480ms
+# next chunk, 100ms
speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
print(rec_result)
@@ -97,7 +99,7 @@
--data_dir "./data/test" \
--output_dir "./results" \
--gpu_inference false \
- --njob 1
+ --njob 64
```
## Finetune with pipeline
--
Gitblit v1.9.1