python/FunASR-XL.git

			@@ -54,15 +54,15 @@

			\| 模型名字 \| 任务详情 \| 训练数据 \| 参数量 \|
			\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------:\|:------------------:\|:------------:\|:----:\|
			\| paraformer-zh ([⭐](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 ( [⭐](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-online ( [⭐](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 ( [⭐](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 ([🤗]() [⭐]() ) \| 语音识别，非实时 \| 50000小时，英文 \| 220M \|
			\| conformer-en ( [⭐](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 ( [⭐](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 ( [⭐](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 ( [⭐](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 <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-online <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 \|


			<a name="快速开始"></a>
			@@ -81,39 +81,59 @@

			### 非实时语音识别
			```python
			from funasr import infer
			from funasr import AutoModel

			p = infer(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", model_hub="ms")
			model = AutoModel(model="paraformer-zh")
			# for the long duration wav, you could add vad model
			# model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad")

			res = p("asr_example_zh.wav", batch_size_token=5000)
			res = model(input="asr_example_zh.wav", batch_size=64)
			print(res)
			```
			注：`model_hub`：表示模型仓库，`ms`为选择modelscope下载，`hf`为选择huggingface下载。

			### 实时语音识别
			```python
			from funasr import infer
			[//]: # (### 实时语音识别)

			p = infer(model="paraformer-zh-streaming", model_hub="ms")
			[//]: # (```python)

			chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
			param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, "encoder_chunk_look_back": 4, "decoder_chunk_look_back": 1}
			[//]: # (from funasr import infer)

			import torchaudio
			speech = torchaudio.load("asr_example_zh.wav")[0][0]
			speech_length = speech.shape[0]
			[//]: # ()
			[//]: # (p = infer(model="paraformer-zh-streaming", model_hub="ms"))

			stride_size = chunk_size[1] * 960
			sample_offset = 0
			for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
			param_dict["is_final"] = True if sample_offset + stride_size >= speech_length - 1 else False
			input = speech[sample_offset: sample_offset + stride_size]
			rec_result = p(input=input, param_dict=param_dict)
			print(rec_result)
			```
			注：`chunk_size`为流式延时配置，`[0,10,5]`表示上屏实时出字粒度为`1060=600ms`，未来信息为`560=300ms`。每次推理输入为`600ms`（采样点数为`16000*0.6=960`），输出为对应文字，最后一个语音片段输入需要设置`is_final=True`来强制输出最后一个字。
			[//]: # ()
			[//]: # (chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms)

			更多详细用法（[新人文档](https://alibaba-damo-academy.github.io/FunASR/en/funasr/quick_start_zh.html)）
			[//]: # (param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, "encoder_chunk_look_back": 4, "decoder_chunk_look_back": 1})

			[//]: # ()
			[//]: # (import torchaudio)

			[//]: # (speech = torchaudio.load("asr_example_zh.wav")[0][0])

			[//]: # (speech_length = speech.shape[0])

			[//]: # ()
			[//]: # (stride_size = chunk_size[1] * 960)

			[//]: # (sample_offset = 0)

			[//]: # (for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):)

			[//]: # ( param_dict["is_final"] = True if sample_offset + stride_size >= speech_length - 1 else False)

			[//]: # ( input = speech[sample_offset: sample_offset + stride_size])

			[//]: # ( rec_result = p(input=input, param_dict=param_dict))

			[//]: # ( print(rec_result))

			[//]: # (```)

			[//]: # (注：`chunk_size`为流式延时配置，`[0,10,5]`表示上屏实时出字粒度为`1060=600ms`，未来信息为`560=300ms`。每次推理输入为`600ms`（采样点数为`16000*0.6=960`），输出为对应文字，最后一个语音片段输入需要设置`is_final=True`来强制输出最后一个字。)

			[//]: # ()
			[//]: # (更多详细用法（[新人文档](https://alibaba-damo-academy.github.io/FunASR/en/funasr/quick_start_zh.html)）)


			<a name="服务部署"></a>
			@@ -140,8 +160,8 @@

			## 社区贡献者

			\| <div align="left"><img src="docs/images/nwpu.png" width="260"/> \| <img src="docs/images/China_Telecom.png" width="200"/> </div> \| <img src="docs/images/RapidAI.png" width="200"/> </div> \| <img src="docs/images/aihealthx.png" width="200"/> </div> \| <img src="docs/images/XVERSE.png" width="250"/> </div> \|
			\|:---------------------------------------------------------------:\|:--------------------------------------------------------------:\|:-------------------------------------------------------:\|:-----------------------------------------------------------:\|:------------------------------------------------------:\|
			\| <div align="left"><img src="docs/images/alibaba.png" width="260"/> \| <div align="left"><img src="docs/images/nwpu.png" width="260"/> \| <img src="docs/images/China_Telecom.png" width="200"/> </div> \| <img src="docs/images/RapidAI.png" width="200"/> </div> \| <img src="docs/images/aihealthx.png" width="200"/> </div> \| <img src="docs/images/XVERSE.png" width="250"/> </div> \|
			\|:------------------------------------------------------------------:\|:---------------------------------------------------------------:\|:--------------------------------------------------------------:\|:-------------------------------------------------------:\|:-----------------------------------------------------------:\|:------------------------------------------------------:\|

			贡献者名单请参考（[致谢名单](./Acknowledge.md)）