leo-speech

Cannot reproduce the RESULTS(wer:43.25%) of S5b_track1 in Chime6

10

When I run the run.sh baseline of S5b_track1 in Chime6, I can't get the wer:43.25% of RESULTS,and I get the best result is wer:45.48% . wer-details: %WER 45.48 [ 26779...

Some warnings for training

4

用finetune.sh在自有数据集上微调下载的speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1 模型时，有一些warning，如下： grad.sizes() = [1, 320], strides() = [1, 1] bucket_view.sizes() = [1, 320], strides() = [320, 1] (Triggered internally at ../torch/csrc/distributed/c10d/reducer.cpp:325.) Variable._execution_engine.run_backward( # Calls into the C++ engine to...

文本输入是“下午三点三十分”会被转为3:30.pm. 当想输出为“下午3:30分”时修改如下： time.tsv里面pm改为下午，同时将time.py的 verbalizer = (hour + addcolon + minute + (addcolon + second).ques + noon.ques) 改为 verbalizer = (noon.ques + hour + addcolon + minute + insert('分') + (addcolon...