jinwater88
jinwater88
@mestrona-3 @BrickDesignerNL Microsoft's AI toolkit has been connected to the NPU version of deepseek-r1-14b, which supports Qualcomm's NPU. Why not consider connecting Microsoft's toolkit to Qualcomm's AIhub? In addition, can...
@whmzsu @TaiYouWeb 遇到的错误是因为 SenseVoice 模型不支持时间戳预测功能,而说话人分离(speaker diarization)依赖于时间戳信息,但是这个时间戳应该可以支持吧,因为VAD检测有时间起始点阿?但是官方没有给出说法,自己写时间戳了
我把paraformer-zh换成sensevoice-small,报错 ERROR:root:Only 'iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch' and 'iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' can predict timestamp, and speaker diarization relies on timestamps. Traceback (most recent call last): File "/media/DataWork/code/sensevoice/test_funasr.py", line 50, in res = model.generate( File "/media/DataWork/code/sensevoice/./FunASR-main/funasr/auto/auto_model.py", line...
torch=2.4.0+cu118,flash_attn-2.6.2+cu118torch2.4cxx11abiTRUE-cp312-cp312-linux_x86_64.whl+python3.12 I have this problem too, have you solved it?
我也想使用sensevoice-small+Cam++进行上述的功能,但是无奈报错,目前仅仅支持paraformer模型+cam++,请问你解决了吗?
Git is not installed
torch=2.4.0+cu118,flash_attn-2.6.2+cu118torch2.4cxx11abiTRUE-cp312-cp312-linux_x86_64.whl+python3.12 I have this problem too, have you solved it?
我遇到这种情况,估计还不支持CAM++,你现在解决了吗
Is there any OpenVino reasoning for the SenseVoice speech model? https://github.com/FunAudioLLM/SenseVoice?tab=readme-ov-file,I only see WhisperPipeline for whisper, so how should I operate if I change to other speech recognition models?