speech_recognition/SenseVoice
1
0
Fork 0
mirror of https://github.com/FunAudioLLM/SenseVoice.git synced 2025-09-15 15:08:35 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

add postprocess for sensevoice

Browse Source
This commit is contained in:
北念 2024-07-10 11:36:55 +08:00
parent 771252c097
commit 831cd02798
3 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -118,6 +118,7 @@ print(res)
```python
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
model_dir = "iic/SenseVoiceSmall"
input_file = (
@ -137,7 +138,9 @@ res = model.generate(
batch_size_s=0,
)
print(res)
text = rich_transcription_postprocess(res[0]["text"])
print(text)
```
The funasr version has integrated the VAD (Voice Activity Detection) model and supports audio input of any duration, with `batch_size_s` in seconds.

5
README_zh.md
View File

@ -118,6 +118,7 @@ print(res)
```python
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
model_dir = "iic/SenseVoiceSmall"
input_file = (
@ -137,7 +138,9 @@ res = model.generate(
batch_size_s=0,
)
print(res)
text = rich_transcription_postprocess(res[0]["text"])
print(text)
```
funasr版本已经集成了vad模型，支持任意时长音频输入，`batch_size_s`单位为秒。

5
demo_funasr.py
View File

@ -4,6 +4,7 @@
# MIT License (https://opensource.org/licenses/MIT)
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
model_dir = "iic/SenseVoiceSmall"
input_file = (
@ -22,4 +23,6 @@ res = model.generate(
use_itn=False,
)
print(res)
text = rich_transcription_postprocess(res[0]["text"])
print(text)