From a3bb4013c39faa1d006dcb4d6d87ec9a6bb3770c Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 27 二月 2024 10:06:22 +0800
Subject: [PATCH] vad
---
README.md | 16 +++++++---------
1 files changed, 7 insertions(+), 9 deletions(-)
diff --git a/README.md b/README.md
index 22c53da..04a3e68 100644
--- a/README.md
+++ b/README.md
@@ -105,10 +105,8 @@
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,
@@ -125,7 +123,7 @@
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
@@ -148,7 +146,7 @@
```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)
@@ -160,7 +158,7 @@
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
@@ -188,7 +186,7 @@
```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)
```
@@ -196,7 +194,7 @@
```python
from funasr import AutoModel
-model = AutoModel(model="fa-zh", model_revision="v2.0.4")
+model = AutoModel(model="fa-zh")
wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/text.txt"
res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
--
Gitblit v1.9.1