From c229c401f3050f99b2501864ed3fcec88e367f22 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 19 四月 2023 23:54:35 +0800
Subject: [PATCH] docs
---
docs/modescope_pipeline/asr_pipeline.md | 34 ++++++++++++++++++++++++++++++----
1 files changed, 30 insertions(+), 4 deletions(-)
diff --git a/docs/modescope_pipeline/asr_pipeline.md b/docs/modescope_pipeline/asr_pipeline.md
index de015b0..db46de3 100644
--- a/docs/modescope_pipeline/asr_pipeline.md
+++ b/docs/modescope_pipeline/asr_pipeline.md
@@ -1,9 +1,13 @@
# Speech Recognition
+.. HINT::
+
+
+ The modelscope pipeline supports all the models in [model zoo] to inference and finetine. Here we take model of Paraformer and Paraformer-online as example to demonstrate the usage.
## Inference
### Quick start
-#### Paraformer model
+#### [Paraformer model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
```python
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
@@ -16,6 +20,27 @@
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 model](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
+```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
@@ -39,11 +64,12 @@
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
+### Inference with you data
-#### Inference with multi GPU
+### Inference with multi-threads on CPU
+
+### Inference with multi GPU
## Finetune with pipeline
--
Gitblit v1.9.1