speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

vad

Browse Source
This commit is contained in:
游雁 2024-02-27 10:06:22 +08:00
parent 1b21c1120c
commit a3bb4013c3
1 changed files with 7 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -105,10 +105,8 @@ Notes: Support recognition of single audio file, as well as file list in Kaldi-s
from funasr import AutoModel from funasr import AutoModel
# paraformer-zh is a multi-functional asr model # paraformer-zh is a multi-functional asr model
# use vad, punc, spk or not as you need # use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh", model_revision="v2.0.4", model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc-c",
vad_model="fsmn-vad", vad_model_revision="v2.0.4", # spk_model="cam++",
punc_model="ct-punc-c", punc_model_revision="v2.0.4",
# spk_model="cam++", spk_model_revision="v2.0.2",
) )
res = model.generate(input=f"{model.model_path}/example/asr_example.wav", res = model.generate(input=f"{model.model_path}/example/asr_example.wav",
batch_size_s=300, batch_size_s=300,
@ -125,7 +123,7 @@ chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention 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 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 soundfile
import os import os
@ -148,7 +146,7 @@ Note: `chunk_size` is the configuration for streaming latency.` [0,10,5]` indica
```python ```python
from funasr import AutoModel 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" wav_file = f"{model.model_path}/example/asr_example.wav"
res = model.generate(input=wav_file) res = model.generate(input=wav_file)
print(res) print(res)
@ -160,7 +158,7 @@ Note: The output format of the VAD model is: `[[beg1, end1], [beg2, end2], ...,
from funasr import AutoModel from funasr import AutoModel
chunk_size = 200 # ms chunk_size = 200 # ms
model = AutoModel(model="fsmn-vad", model_revision="v2.0.4") model = AutoModel(model="fsmn-vad")
import soundfile import soundfile
@ -188,7 +186,7 @@ The output is measured in milliseconds and represents the absolute time from the
```python ```python
from funasr import AutoModel from funasr import AutoModel
model = AutoModel(model="ct-punc", model_revision="v2.0.4") model = AutoModel(model="ct-punc")
res = model.generate(input="那今天的会就到这里吧 happy new year 明年见") res = model.generate(input="那今天的会就到这里吧 happy new year 明年见")
print(res) print(res)
``` ```
@ -196,7 +194,7 @@ print(res)
```python ```python
from funasr import AutoModel 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" wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/text.txt" text_file = f"{model.model_path}/example/text.txt"
res = model.generate(input=(wav_file, text_file), data_type=("sound", "text")) res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))