From 2e36e738ca39afc8d02f3d11013bd12f937cc874 Mon Sep 17 00:00:00 2001
From: zhaomingwork <61895407+zhaomingwork@users.noreply.github.com>
Date: 星期三, 08 十一月 2023 09:22:06 +0800
Subject: [PATCH] fix bug for h5 hotwords (#1067)
---
egs_modelscope/asr/TEMPLATE/README.md | 69 ++++++++++++++++++++++++++++++++++
1 files changed, 68 insertions(+), 1 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index 4cf6a7e..bf6d30b 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -21,6 +21,34 @@
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-long 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
+
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+ vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+ #punc_model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
+ punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large',
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav',
+ batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000)
+print(rec_result)
+```
+
+Where,
+- `batch_size_token` refs to dynamic batch_size and the total tokens of batch is `batch_size_token`, 1 token = 60 ms.
+- `batch_size_token_threshold_s`: The batch_size is set to 1, when the audio duration exceeds the threshold value of `batch_size_token_threshold_s`, specified in `s`.
+- `max_single_segment_time`: The maximum length for audio segmentation in VAD, specified in `ms`.
+
+Suggestion: When encountering OOM (Out of Memory) issues with long audio inputs, as the GPU memory usage increases with the square of the audio duration, there are three possible scenarios:
+- a) In the initial inference stage, GPU memory usage primarily depends on `batch_size_token`. Reducing this value appropriately can help reduce memory usage.
+- b) In the middle of the inference process, when encountering long audio segments segmented by VAD, if the total number of tokens is still smaller than `batch_size_token` but OOM issues persist, reducing `batch_size_token_threshold_s` can help. If the threshold is exceeded, forcing the batch size to 1 can be considered.
+- c) Towards the end of the inference process, when encountering long audio segments segmented by VAD and the total number of tokens is smaller than `batch_size_token` but exceeds the threshold `batch_size_token_threshold_s`, forcing the batch size to 1 may still result in OOM errors. In such cases, reducing `max_single_segment_time` can be considered to shorten the duration of audio segments generated by VAD.
+
#### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
##### Streaming Decoding
```python
@@ -68,6 +96,23 @@
```
Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
+#### [Paraformer-contextual Model](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+param_dict = dict()
+# param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
+param_dict['hotword']="閭撻儊鏉� 鐜嬮鏄� 鐜嬫檾鍚�"
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
+ param_dict=param_dict)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav')
+print(rec_result)
+```
+
#### [UniASR Model](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
There are three decoding mode for UniASR model(`fast`銆乣normal`銆乣offline`), for more model details, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
```python
@@ -82,6 +127,28 @@
```
The decoding mode of `fast` and `normal` is fake streaming, which could be used for evaluating of recognition accuracy.
Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
+
+#### [Paraformer-Spk](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary)
+This model allows user to get recognition results which contain speaker info of each sentence. Refer to [CAM++](https://modelscope.cn/models/damo/speech_campplus_speaker-diarization_common/summary) for detailed information about speaker diarization model.
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == '__main__':
+ audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_speaker_demo.wav'
+ output_dir = "./results"
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn',
+ model_revision='v0.0.2',
+ vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+ punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large',
+ output_dir=output_dir,
+ )
+ rec_result = inference_pipeline(audio_in=audio_in, batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000)
+ print(rec_result)
+```
+
#### [RNN-T-online model]()
Undo
@@ -202,7 +269,7 @@
if __name__ == '__main__':
params = modelscope_args(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", data_path="./data")
params.output_dir = "./checkpoint" # m妯″瀷淇濆瓨璺緞
- params.data_path = "./example_data/" # 鏁版嵁璺緞
+ params.data_path = "speech_asr_aishell1_trainsets" # 鏁版嵁璺緞
params.dataset_type = "small" # 灏忔暟鎹噺璁剧疆small锛岃嫢鏁版嵁閲忓ぇ浜�1000灏忔椂锛岃浣跨敤large
params.batch_bins = 2000 # batch size锛屽鏋渄ataset_type="small"锛宐atch_bins鍗曚綅涓篺bank鐗瑰緛甯ф暟锛屽鏋渄ataset_type="large"锛宐atch_bins鍗曚綅涓烘绉掞紝
params.max_epoch = 20 # 鏈�澶ц缁冭疆鏁�
--
Gitblit v1.9.1