From b141ac79906f677d794ab3d67fc47e6074499c8d Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 25 四月 2023 15:48:27 +0800
Subject: [PATCH] Merge pull request #415 from alibaba-damo-academy/dev_yf
---
egs_modelscope/asr/TEMPLATE/README.md | 35 +++++++++++++++++++++++++++++++++--
1 files changed, 33 insertions(+), 2 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index 543a659..b7e76cb 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -58,6 +58,22 @@
#### [RNN-T-online model]()
Undo
+#### [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`
@@ -72,7 +88,7 @@
- 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
@@ -176,6 +192,21 @@
- `max_epoch`: number of training epoch
- `lr`: learning rate
+- Training data formats锛�
+```sh
+cat ./example_data/text
+BAC009S0002W0122 鑰� 瀵� 妤� 甯� 鎴� 浜� 鎶� 鍒� 浣� 鐢� 鏈� 澶� 鐨� 闄� 璐�
+BAC009S0002W0123 涔� 鎴� 涓� 鍦� 鏂� 鏀� 搴� 鐨� 鐪� 涓� 閽�
+english_example_1 hello world
+english_example_2 go swim 鍘� 娓� 娉�
+
+cat ./example_data/wav.scp
+BAC009S0002W0122 /mnt/data/wav/train/S0002/BAC009S0002W0122.wav
+BAC009S0002W0123 /mnt/data/wav/train/S0002/BAC009S0002W0123.wav
+english_example_1 /mnt/data/wav/train/S0002/english_example_1.wav
+english_example_2 /mnt/data/wav/train/S0002/english_example_2.wav
+```
+
- Then you can run the pipeline to finetune with:
```shell
python finetune.py
@@ -210,4 +241,4 @@
--njob 64 \
--checkpoint_dir "./checkpoint" \
--checkpoint_name "valid.cer_ctc.ave.pb"
-```
\ No newline at end of file
+```
--
Gitblit v1.9.1