add postprocess for sensevoice

AndersonBY · Jul 10, 2024 · 831cd02 · 831cd02
1 parent 771252c
commit 831cd02
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -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.

diff --git a/README_zh.md b/README_zh.md
@@ -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。

diff --git a/demo_funasr.py b/demo_funasr.py
@@ -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 @@
     use_itn=False,
 )
 
-print(res)
+text = rich_transcription_postprocess(res[0]["text"])
+
+print(text)