From 30aa982bf29ceefaf52c0013c12c19adc57dea0e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 27 四月 2023 21:11:04 +0800
Subject: [PATCH] docs
---
egs_modelscope/asr/TEMPLATE/README.md | 40 ++++++++++++++++++++++++++++++----------
1 files changed, 30 insertions(+), 10 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index fd69ea1..28a31a2 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -19,22 +19,24 @@
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)
+#### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_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',
+ model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
+ model_revision='v1.0.4'
)
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
+chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
+chunk_stride = chunk_size[1] * 960 # 600ms銆�480ms
+# first chunk, 600ms
speech_chunk = speech[0:chunk_stride]
rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
print(rec_result)
-# next chunk, 480ms
+# next chunk, 600ms
speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
print(rec_result)
@@ -58,21 +60,37 @@
#### [RNN-T-online model]()
Undo
-#### API-reference
-##### Define pipeline
+#### [MFCCA Model](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
+For more model detailes, please refer to [docs](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
+ model_revision='v3.0.0'
+)
+
+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)
+```
+
+### API-reference
+#### Define pipeline
- `task`: `Tasks.auto_speech_recognition`
- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
- `ngpu`: `1` (Default), decoding on GPU. If ngpu=0, decoding on CPU
- `ncpu`: `1` (Default), sets the number of threads used for intraop parallelism on CPU
- `output_dir`: `None` (Default), the output path of results if set
- `batch_size`: `1` (Default), batch size when decoding
-##### Infer pipeline
+#### Infer pipeline
- `audio_in`: the input to decode, which could be:
- wav_path, `e.g.`: asr_example.wav,
- pcm_path, `e.g.`: asr_example.pcm,
- audio bytes stream, `e.g.`: bytes data from a microphone
- audio sample point锛宍e.g.`: `audio, rate = soundfile.read("asr_example_zh.wav")`, the dtype is numpy.ndarray or torch.Tensor
- - wav.scp, kaldi style wav list (`wav_id \t wav_path``), `e.g.`:
+ - wav.scp, kaldi style wav list (`wav_id \t wav_path`), `e.g.`:
```text
asr_example1 ./audios/asr_example1.wav
asr_example2 ./audios/asr_example2.wav
@@ -94,6 +112,8 @@
- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
+ - `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast銆乶ormal銆乷ffline)
+ - `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
- Decode with multi GPUs:
```shell
--
Gitblit v1.9.1