docs

游雁

2023-04-19 e1efa5703832696940fd2fe8fd4410fcc2e1beab

docs

 docs/FQA.md

@@ -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)

 docs/modescope_pipeline/asr_pipeline.md

@@ -16,6 +16,27 @@
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 @@
  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