mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
sensevoice
This commit is contained in:
parent
774caaf752
commit
374998bd36
@ -69,6 +69,34 @@ res = model.generate(input=[str], output_dir=[str])
|
|||||||
|
|
||||||
|
|
||||||
#### Speech Recognition (Non-streaming)
|
#### 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
|
```python
|
||||||
from funasr import AutoModel
|
from funasr import AutoModel
|
||||||
# paraformer-zh is a multi-functional asr model
|
# paraformer-zh is a multi-functional asr model
|
||||||
|
|||||||
@ -70,6 +70,34 @@ res = model.generate(input=[str], output_dir=[str])
|
|||||||
|
|
||||||
|
|
||||||
#### 非实时语音识别
|
#### 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
|
```python
|
||||||
from funasr import AutoModel
|
from funasr import AutoModel
|
||||||
# paraformer-zh is a multi-functional asr model
|
# paraformer-zh is a multi-functional asr model
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user