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_zh.md | 51 +++++++++++++++++++++++++++++++++++++++++++++++----
1 files changed, 47 insertions(+), 4 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/README_zh.md b/egs_modelscope/asr/TEMPLATE/README_zh.md
index 81e0271..47656b3 100644
--- a/egs_modelscope/asr/TEMPLATE/README_zh.md
+++ b/egs_modelscope/asr/TEMPLATE/README_zh.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)
```
婕旂ず浠ｇ爜瀹屾暣鐗堟湰锛岃鍙傝�僛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 妯″瀷](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
UniASR 妯″瀷鏈変笁绉嶈В鐮佹ā寮�(fast銆乶ormal銆乷ffline)锛屾洿澶氭ā鍨嬬粏鑺傝鍙傝�僛鏂囨。](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
@@ -80,6 +100,29 @@
fast 鍜� normal 鐨勮В鐮佹ā寮忔槸鍋囨祦寮忚В鐮侊紝鍙敤浜庤瘎浼拌瘑鍒噯纭�с��
婕旂ず鐨勫畬鏁翠唬鐮侊紝璇峰弬瑙� [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
+#### [Paraformer-Spk model](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary)
+杩斿洖璇嗗埆缁撴灉鐨勫悓鏃惰繑鍥炴瘡涓瓙鍙ョ殑璇磋瘽浜哄垎绫荤粨鏋溿�傚叧浜庤璇濅汉鏃ュ織妯″瀷鐨勮鎯呰瑙乕CAM++](https://modelscope.cn/models/damo/speech_campplus_speaker-diarization_common/summary)銆�
+
+```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 妯″瀷]()
Undo
--
Gitblit v1.9.1