From 774caaf75222a42a9663574571cb85025b5e056a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=B8=E9=9B=81?= <zhifu.gzf@alibaba-inc.com>
Date: Tue, 16 Jul 2024 14:27:13 +0800
Subject: [PATCH] sensevoice

---
 README.md    | 28 ++++++++++++++++++++++++++++
 README_zh.md | 28 ++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+)

diff --git a/README.md b/README.md
index 4638ab36e..3a99b99e5 100644
--- a/README.md
+++ b/README.md
@@ -129,6 +129,34 @@ funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++inp
 Notes: Support recognition of single audio file, as well as file list in Kaldi-style wav.scp format: `wav_id wav_pat`
 
 ### Speech Recognition (Non-streaming)
+#### SenseVoice
+```python
+from funasr import AutoModel
+from funasr.utils.postprocess_utils import rich_transcription_postprocess
+
+model_dir = "iic/SenseVoiceSmall"
+
+model = AutoModel(
+    model=model_dir,
+    vad_model="fsmn-vad",
+    vad_kwargs={"max_single_segment_time": 30000},
+    device="cuda:0",
+)
+
+# en
+res = model.generate(
+    input=f"{model.model_path}/example/en.mp3",
+    cache={},
+    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
+    use_itn=True,
+    batch_size_s=60,
+    merge_vad=True,  #
+    merge_length_s=15,
+)
+text = rich_transcription_postprocess(res[0]["text"])
+print(text)
+```
+#### Paraformer
 ```python
 from funasr import AutoModel
 # paraformer-zh is a multi-functional asr model
diff --git a/README_zh.md b/README_zh.md
index 275a30d6f..70a6d25b8 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -128,6 +128,34 @@ funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++inp
 注：支持单条音频文件识别，也支持文件列表，列表为kaldi风格wav.scp：`wav_id   wav_path`
 
 ### 非实时语音识别
+#### SenseVoice
+```python
+from funasr import AutoModel
+from funasr.utils.postprocess_utils import rich_transcription_postprocess
+
+model_dir = "iic/SenseVoiceSmall"
+
+model = AutoModel(
+    model=model_dir,
+    vad_model="fsmn-vad",
+    vad_kwargs={"max_single_segment_time": 30000},
+    device="cuda:0",
+)
+
+# en
+res = model.generate(
+    input=f"{model.model_path}/example/en.mp3",
+    cache={},
+    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
+    use_itn=True,
+    batch_size_s=60,
+    merge_vad=True,  #
+    merge_length_s=15,
+)
+text = rich_transcription_postprocess(res[0]["text"])
+print(text)
+```
+#### Paraformer
 ```python
 from funasr import AutoModel
 # paraformer-zh is a multi-functional asr model