From 1b21c1120c447f2d6f012b00bb94ea97bfc9f92c Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 27 二月 2024 10:00:22 +0800
Subject: [PATCH] vad

---
 examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py |    8 ++++++++
 README_zh.md                                                    |   24 +++++++++++++++---------
 README.md                                                       |    9 +++++++++
 3 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index 454adc9..22c53da 100644
--- a/README.md
+++ b/README.md
@@ -153,6 +153,8 @@
 res = model.generate(input=wav_file)
 print(res)
 ```
+Note: The output format of the VAD model is: `[[beg1, end1], [beg2, end2], ..., [begN, endN]]`, where `begN/endN` indicates the starting/ending point of the `N-th` valid audio segment, measured in milliseconds.
+
 ### Voice Activity Detection (Streaming)
 ```python
 from funasr import AutoModel
@@ -175,6 +177,13 @@
     if len(res[0]["value"]):
         print(res)
 ```
+Note: The output format for the streaming VAD model can be one of four scenarios:
+- `[[beg1, end1], [beg2, end2], .., [begN, endN]]`锛歍he same as the offline VAD output result mentioned above.
+- `[[beg, -1]]`锛欼ndicates that only a starting point has been detected.
+- `[[-1, end]]`锛欼ndicates that only an ending point has been detected.
+- `[]`锛欼ndicates that neither a starting point nor an ending point has been detected. 
+
+The output is measured in milliseconds and represents the absolute time from the starting point.
 ### Punctuation Restoration
 ```python
 from funasr import AutoModel
diff --git a/README_zh.md b/README_zh.md
index 07cdd1f..63ad2e2 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -101,10 +101,8 @@
 from funasr import AutoModel
 # paraformer-zh is a multi-functional asr model
 # use vad, punc, spk or not as you need
-model = AutoModel(model="paraformer-zh", model_revision="v2.0.4",
-                  vad_model="fsmn-vad", vad_model_revision="v2.0.4",
-                  punc_model="ct-punc-c", punc_model_revision="v2.0.4",
-                  # spk_model="cam++", spk_model_revision="v2.0.2",
+model = AutoModel(model="paraformer-zh",  vad_model="fsmn-vad", punc_model="ct-punc-c", 
+                  # spk_model="cam++"
                   )
 res = model.generate(input=f"{model.model_path}/example/asr_example.wav", 
             batch_size_s=300, 
@@ -122,7 +120,7 @@
 encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
 decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
 
-model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.4")
+model = AutoModel(model="paraformer-zh-streaming")
 
 import soundfile
 import os
@@ -146,19 +144,21 @@
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
+model = AutoModel(model="fsmn-vad")
 
 wav_file = f"{model.model_path}/example/asr_example.wav"
 res = model.generate(input=wav_file)
 print(res)
 ```
+娉細VAD妯″瀷杈撳嚭鏍煎紡涓猴細`[[beg1, end1], [beg2, end2], .., [begN, endN]]`锛屽叾涓璥begN/endN`琛ㄧず绗琡N`涓湁鏁堥煶棰戠墖娈电殑璧峰鐐�/缁撴潫鐐癸紝
+鍗曚綅涓烘绉掋��
 
 ### 璇煶绔偣妫�娴嬶紙瀹炴椂锛�
 ```python
 from funasr import AutoModel
 
 chunk_size = 200 # ms
-model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
+model = AutoModel(model="fsmn-vad")
 
 import soundfile
 
@@ -175,12 +175,18 @@
     if len(res[0]["value"]):
         print(res)
 ```
+娉細娴佸紡VAD妯″瀷杈撳嚭鏍煎紡涓�4绉嶆儏鍐碉細
+- `[[beg1, end1], [beg2, end2], .., [begN, endN]]`锛氬悓涓婄绾縑AD杈撳嚭缁撴灉銆�
+- `[[beg, -1]]`锛氳〃绀哄彧妫�娴嬪埌璧峰鐐广��
+- `[[-1, end]]`锛氳〃绀哄彧妫�娴嬪埌缁撴潫鐐广��
+- `[]`锛氳〃绀烘棦娌℃湁妫�娴嬪埌璧峰鐐癸紝涔熸病鏈夋娴嬪埌缁撴潫鐐�
+杈撳嚭缁撴灉鍗曚綅涓烘绉掞紝浠庤捣濮嬬偣寮�濮嬬殑缁濆鏃堕棿銆�
 
 ### 鏍囩偣鎭㈠
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="ct-punc", model_revision="v2.0.4")
+model = AutoModel(model="ct-punc")
 
 res = model.generate(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
 print(res)
@@ -190,7 +196,7 @@
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="fa-zh", model_revision="v2.0.0")
+model = AutoModel(model="fa-zh")
 
 wav_file = f"{model.model_path}/example/asr_example.wav"
 text_file = f"{model.model_path}/example/text.txt"
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
index f043123..c28db7a 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
@@ -10,6 +10,8 @@
 
 res = model.generate(input=wav_file)
 print(res)
+# [[beg1, end1], [beg2, end2], .., [begN, endN]]
+# beg/end: ms
 
 
 
@@ -37,3 +39,9 @@
     # print(res)
     if len(res[0]["value"]):
         print(res)
+
+
+# 1. [[beg1, end1], [beg2, end2], .., [begN, endN]]; [[beg, end]]; [[beg1, end1], [beg2, end2]]
+# 2. [[beg, -1]]
+# 3. [[-1, end]]
+# beg/end: ms
\ No newline at end of file

--
Gitblit v1.9.1