Repository Issue Activity (beta)

#2816 wetext build problem

#2814 Upgrade CXX Standard from 14 to 17 ?

#2808 aishell阶段8.2没有输出

#2815 Comparison: FunASR/SenseVoice — similar production ASR goals, complementary strengths

#2807 Multilingual Model Training

#1035 想问下如何进行热词添加？

#2794 GPU fp16 onnx模型导出问题

#2805 Does this repo support self supervised pretraining and finetuning?

#2804 关于sensevoice-small训练的示例

#2803 使用新版Android Studio编译android示例项目出现空指针异常

#2788 貌似torch.autocast和deepspeed不能直接融合，运行实例会报错

#2795 Runtime on web is not working anymore with final.zip and units.txt

#2790 CL不支持当前 python==3.10.18环境

#2616 【Help needed】训练迭代一定step后开始频繁出现loss = nan的情况

#2763 ctc loss无法降低

#2787 [discussion] about the performance of the best-rq model

#2786 Regarding the fine-tuning Whisper models for streaming capabilities in other languages

#2722 runtime libtorch编译

#2767 微调数据量大概需要多少才能有比较不错的效果

#2785 三方依赖libFuzzer库目前是不能拉取的状态，会导致cmake配置失败

#2782 Regarding the fine-tuning of the Whisper model using the "pytorch_model.bin" file generated by DeepSpeed.

#2765 使用shard方式拉取网络数据，tar解压报错

#2766 安卓apk点击START RECORD闪退

#2793 QUESTION: Pre-trained Whisper model and streaming support

#2764 RuntimeError: "ctc_loss_cuda" not implemented for 'BFloat16'