python/FunASR-XL.git

			@@ -60,14 +60,13 @@
			\| 模型名字 \| 任务详情 \| 训练数据 \| 参数量 \|
			\|:------------------------------------------------------------------------------------------------------------------------------------------------------------:\|:------------------:\|:------------:\|:----:\|
			\| paraformer-zh <br> ([⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [🤗]() ) \| 语音识别，带时间戳输出，非实时 \| 60000小时，中文 \| 220M \|
			\| paraformer-zh-spk <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [🤗]() ) \| 分角色语音识别，带时间戳输出，非实时 \| 60000小时，中文 \| 220M \|
			\| paraformer-zh-streaming <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() ) \| 语音识别，实时 \| 60000小时，中文 \| 220M \|
			\| paraformer-en <br> ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() ) \| 语音识别，非实时 \| 50000小时，英文 \| 220M \|
			\| paraformer-en-spk <br> ([⭐]() [🤗]() ) \| 语音识别，非实时 \| 50000小时，英文 \| 220M \|
			\| conformer-en <br> ( [⭐](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [🤗]() ) \| 语音识别，非实时 \| 50000小时，英文 \| 220M \|
			\| ct-punc <br> ( [⭐](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗]() ) \| 标点恢复 \| 100M，中文与英文 \| 1.1G \|
			\| fsmn-vad <br> ( [⭐](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗]() ) \| 语音端点检测，实时 \| 5000小时，中文与英文 \| 0.4M \|
			\| fa-zh <br> ( [⭐](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [🤗]() ) \| 字级别时间戳预测 \| 50000小时，中文 \| 38M \|
			\| paraformer-zh-spk <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [🤗]() ) \| 分角色语音识别，带时间戳输出，非实时 \| 60000小时，中文 \| 220M \|
			\| paraformer-zh-streaming <br> ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() ) \| 语音识别，实时 \| 60000小时，中文 \| 220M \|
			\| paraformer-en <br> ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() ) \| 语音识别，非实时 \| 50000小时，英文 \| 220M \|
			\| conformer-en <br> ( [⭐](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [🤗]() ) \| 语音识别，非实时 \| 50000小时，英文 \| 220M \|
			\| ct-punc <br> ( [⭐](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗]() ) \| 标点恢复 \| 100M，中文与英文 \| 1.1G \|
			\| fsmn-vad <br> ( [⭐](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗]() ) \| 语音端点检测，实时 \| 5000小时，中文与英文 \| 0.4M \|
			\| fa-zh <br> ( [⭐](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [🤗]() ) \| 字级别时间戳预测 \| 50000小时，中文 \| 38M \|


			<a name="快速开始"></a>
			@@ -92,7 +91,7 @@
			vad_model="fsmn-vad", vad_model_revision="v2.0.2", \
			punc_model="ct-punc-c", punc_model_revision="v2.0.2", \
			spk_model="cam++", spk_model_revision="v2.0.2")
			res = model(input=f"{model.model_path}/example/asr_example.wav",
			res = model.generate(input=f"{model.model_path}/example/asr_example.wav",
			batch_size=64,
			hotword='魔搭')
			print(res)
			@@ -122,7 +121,7 @@
			for i in range(total_chunk_num):
			speech_chunk = speech[ichunk_stride:(i+1)chunk_stride]
			is_final = i == total_chunk_num - 1
			res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
			res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
			print(res)
			```

			@@ -135,7 +134,7 @@
			model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")

			wav_file = f"{model.model_path}/example/asr_example.wav"
			res = model(input=wav_file)
			res = model.generate(input=wav_file)
			print(res)
			```

			@@ -157,7 +156,7 @@
			for i in range(total_chunk_num):
			speech_chunk = speech[ichunk_stride:(i+1)chunk_stride]
			is_final = i == total_chunk_num - 1
			res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
			res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
			if len(res[0]["value"]):
			print(res)
			```
			@@ -168,7 +167,7 @@

			model = AutoModel(model="ct-punc", model_revision="v2.0.2")

			res = model(input="那今天的会就到这里吧 happy new year 明年见")
			res = model.generate(input="那今天的会就到这里吧 happy new year 明年见")
			print(res)
			```

			@@ -180,10 +179,10 @@

			wav_file = f"{model.model_path}/example/asr_example.wav"
			text_file = f"{model.model_path}/example/text.txt"
			res = model(input=(wav_file, text_file), data_type=("sound", "text"))
			res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
			print(res)
			```
			更多详细用法（[示例](examples/industrial_data_pretraining)）
			更多详细用法（[示例](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)）


			<a name="服务部署"></a>
			@@ -243,4 +242,10 @@
			pages={2063--2067},
			doi={10.21437/Interspeech.2022-9996}
			}
			@article{shi2023seaco,
			author={Xian Shi and Yexin Yang and Zerui Li and Yanni Chen and Zhifu Gao and Shiliang Zhang},
			title={{SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability}},
			year=2023,
			journal={arXiv preprint arXiv:2308.03266(accepted by ICASSP2024)},
			}
			```