%WER 49.32 [ 34366 / 69674, 3467 ins, 7533 del, 23366 sub ] exp/mono/decode_test120_p_spk/wer_9_0.0
%WER 24.33 [ 16949 / 69674, 2512 ins, 3034 del, 11403 sub ] exp/tri1/decode_test120_p_spk/wer_14_0.5
%WER 24.00 [ 16719 / 69674, 2874 ins, 2543 del, 11302 sub ] exp/tri2a/decode_test120_p_spk/wer_13_0.5
%WER 22.60 [ 15747 / 69674, 2838 ins, 2438 del, 10471 sub ] exp/tri2b/decode_test120_p_spk/wer_15_0.5
%WER 20.27 [ 14120 / 69674, 2952 ins, 1851 del, 9317 sub ] exp/tri3b/decode_test120_p_spk/wer_16_0.0
%WER 19.00 [ 13238 / 69674, 2999 ins, 1576 del, 8663 sub ] exp/tri4a/decode_test120_p_spk/wer_17_0.0
%WER 21.77 [ 15168 / 69674, 2783 ins, 2214 del, 10171 sub ] exp/nnet5c/decode_test120_p_spk/wer_12_0.0
jimregan/kaldi-sprakbanken_swe
一条命令提交
在你的模型文件夹旁边运行它。它会制作种子、将文件与 Hugging Face 比对，然后提交。你只需开始做种，并粘贴你账户中的密钥。它只读取你的文件，绝不修改。如果愿意，可以先阅读脚本。
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo jimregan/kaldi-sprakbanken_swe ./model-folder