FunASR

FunASR copied to clipboard

四川话识别哪个最优

1

Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节） ## ❓ Questions and Help 您好，请问下哪个模型对四川话识别效果最好 ### Before asking: 1. search the issues. 2. search...

wcool1

Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节） ## ❓ Questions and Help 这两个缓存似乎没有参与任何运算，它们存在的意义是什么 https://github.com/modelscope/FunASR/blob/main/funasr/frontends/wav_frontend.py#L491 https://github.com/modelscope/FunASR/blob/main/funasr/frontends/wav_frontend.py#L494 ### Before asking: 1. search the issues....

CaptainNeil

多个音频asr后有1个字的时间戳偏移

1

版本：funasr 1.2.6 模型：iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch 使用上述版本提取timestamp和文本有1个字的时间戳偏移。

czydfj

IndexError: index 2 is out of bounds for dimension 1 with size 2

5

Process Process-6: Traceback (most recent call last): File "/root/miniconda3/envs/sensevoice/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/root/miniconda3/envs/sensevoice/lib/python3.10/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/usr/local/data2/workspace/egs_vocal_extractor/data/speech_det.py", line 156, in process_audio_task res =...

passerbya

AssertionError: EParaformer is not registered

2

训练e-paraformer的时候报错“AssertionError: EParaformer is not registered”，进一步寻找发现e_paraformer的model.py “from funasr.models.transformer.utils.add_sos_eos import add_sos_eos, add_sos_and_eos” 导入错误，是由于funasr.models.transformer.utils.add_sos_eos 下面没有add_sos_and_eos这个函数。

Meeny2018

Problems to use vad_model, pucn_model and spk_model with streaming voice. 如何正常在流式处理中加载这3个模型?

6

## 仿照readme.md尝试加载多个模型流式处理, 遇到问题 keyword: fsmn-vad, ct-punc, cam++, is_final #### What have you tried? **step1:** 复制readme.md中Speech Recognition (Streaming) 这一节的代码, 其中 `model = AutoModel(model="paraformer-zh-streaming"`, 运行正常 (完整代码和readme.md相同, 贴在最后一部分方便阅读) **step2:** 将示例代码的model修改为: ``` model =...

1113200320

支不支持opus音频格式识别？

1

支不支持opus或mp3音频格式识别？

KabourWu

官网给的funasr_wss_server报错

3

Traceback (most recent call last): File "D:\MyProject\FunASR-main\runtime\python\websocket\funasr_wss_server.py", line 337, in start_server = websockets.serve( File "D:\soft\Python3.9\Lib\site-packages\websockets\asyncio\server.py", line 740, in __init__ self.server = Server( File "D:\soft\Python3.9\Lib\site-packages\websockets\asyncio\server.py", line 282, in __init__ self.loop =...

GithubRobot01

服务器部署问题，求大佬帮忙

6

 例如这个中文流式语音识别服务文档，如果我是想测试whisper-large-v3的ASR效果，我该如何设置参数，之前已经在modelscope社区下载了模型文件到本地了并传到服务器上了:  请问我该如何设置这个服务端参数？

lower01

## 🐛 Bug funasr.models.transformer.utils.add_sos_eos 里面没有add_sos_and_eos 方法 ### Environment - FunASR Version (e.g., 1.0.0): 1.2.6

tiandiweizun