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

docs

Browse Source
This commit is contained in:
游雁 2023-04-19 23:38:48 +08:00
parent b3e53201da
commit e1efa57038
2 changed files with 35 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
docs/FQA.md
View File

@ -1,22 +1,22 @@
# FQA
## How to use vad, asr and punc model by pipeline
To combine the vad, asr, and punc model pipelines, ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/278)
## How to use VAD model by modelscope pipeline
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/236)
## How to combine vad, asr, punc and nnlm models inside pipeline
ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/134)
## How to use Punctuation model by modelscope pipeline
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/238)
## How to combine timestamp prediction model in ASR pipeline
ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/246)
## How to use Parafomrer model for streaming by modelscope pipeline
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
## How to use VAD decoding in FunASR
ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/236)
## How to use vad, asr and punc model by modelscope pipeline
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/278)
## How to use VAD decoding in FunASR
ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/238)
## How to combine vad, asr, punc and nnlm models inside modelscope pipeline
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/134)
## How to use Punctuation Models in FunASR
ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/238)
## How to combine timestamp prediction model by modelscope pipeline
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/246)
## How to switch decoding mode between online and offline for UniASR model
ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/151)

22
docs/modescope_pipeline/asr_pipeline.md
View File

@ -16,6 +16,27 @@ inference_pipeline = pipeline(
rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
print(rec_result)
```
#### Paraformer-online
```python
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
)
import soundfile
speech, sample_rate = soundfile.read("example/asr_example.wav")
param_dict = {"cache": dict(), "is_final": False}
chunk_stride = 7680# 480ms
# first chunk, 480ms
speech_chunk = speech[0:chunk_stride]
rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
# next chunk, 480ms
speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
print(rec_result)
```
Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
#### API-reference
##### define pipeline
@ -39,6 +60,7 @@ print(rec_result)
In this case of `wav.scp` input, `output_dir` must be set to save the output results
- `audio_fs`: audio sampling rate, only set when audio_in is pcm audio
#### Inference with you data
#### Inference with multi-threads on CPU