From a05e753d11d9c36983ec4e58c421dbcf86d1dcd4 Mon Sep 17 00:00:00 2001
From: Xian Shi <40013335+R1ckShi@users.noreply.github.com>
Date: 星期二, 17 十月 2023 16:47:27 +0800
Subject: [PATCH] Merge branch 'main' into dev_onnx
---
egs_modelscope/asr/TEMPLATE/README.md | 52 +++++++++++++++++++++++++++++++++++++++++++++++-----
1 files changed, 47 insertions(+), 5 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index a8cb486..ac73950 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -27,15 +27,18 @@
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
- model_revision='v1.0.6',
+ model_revision='v1.0.7',
update_model=False,
mode='paraformer_streaming'
)
import soundfile
speech, sample_rate = soundfile.read("example/asr_example.wav")
-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_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
+encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
+decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size,
+ "encoder_chunk_look_back": encoder_chunk_look_back, "decoder_chunk_look_back": decoder_chunk_look_back}
chunk_stride = chunk_size[1] * 960 # 600ms銆�480ms
# first chunk, 600ms
speech_chunk = speech[0:chunk_stride]
@@ -55,7 +58,7 @@
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
- model_revision='v1.0.6',
+ model_revision='v1.0.7',
update_model=False,
mode="paraformer_fake_streaming"
)
@@ -64,6 +67,23 @@
print(rec_result)
```
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)
@@ -79,6 +99,28 @@
```
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
@@ -199,7 +241,7 @@
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