From e1efa5703832696940fd2fe8fd4410fcc2e1beab Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 19 四月 2023 23:38:48 +0800
Subject: [PATCH] docs
---
docs/FQA.md | 26 +++++++++++++-------------
docs/modescope_pipeline/asr_pipeline.md | 22 ++++++++++++++++++++++
2 files changed, 35 insertions(+), 13 deletions(-)
diff --git a/docs/FQA.md b/docs/FQA.md
index de72eea..46c5aa3 100644
--- a/docs/FQA.md
+++ b/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)
\ No newline at end of file
+Ref to [docs](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
\ No newline at end of file
diff --git a/docs/modescope_pipeline/asr_pipeline.md b/docs/modescope_pipeline/asr_pipeline.md
index de015b0..8b7e8b8 100644
--- a/docs/modescope_pipeline/asr_pipeline.md
+++ b/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
--
Gitblit v1.9.1