diff --git a/examples/librispeech/s0/README.md b/examples/librispeech/s0/README.md index e13e8d886..6e09c45a6 100644 --- a/examples/librispeech/s0/README.md +++ b/examples/librispeech/s0/README.md @@ -7,11 +7,17 @@ * Decoding info: ctc_weight 0.3, reverse weight 0.5, average_num 30 * Git hash: 65270043fc8c2476d1ab95e7c39f730017a670e0 * Model link: http://mobvoi-speech-public.ufile.ucloud.cn/public/wenet/librispeech/20210610_conformer_bidecoder_exp.tar.gz +* LM-tgmed: [3-gram.pruned.1e-7.arpa.gz](http://www.openslr.org/resources/11/3-gram.pruned.1e-7.arpa.gz) +* LM-tglarge: [3-gram.arpa.gz](http://www.openslr.org/resources/11/3-gram.arpa.gz) +* LM-fglarge: [4-gram.arpa.gz](http://www.openslr.org/resources/11/4-gram.arpa.gz) -| decoding mode | test clean | test other | -|--------------------------------|------------|------------| -| ctc prefix beam search | 2.96 | 7.14 | -| attention rescoring | 2.66 | 6.53 | +| decoding mode | test clean | test other | +|----------------------------------|------------|------------| +| ctc prefix beam search | 2.96 | 7.14 | +| attention rescoring | 2.66 | 6.53 | +| LM-tgmed + attention rescoring | 2.78 | 6.32 | +| LM-tglarge + attention rescoring | 2.68 | 6.10 | +| LM-fglarge + attention rescoring | 2.65 | 5.98 | ## Conformer Result @@ -20,16 +26,16 @@ * Decoding info: ctc_weight 0.5, average_num 30 * Git hash: 90d9a559840e765e82119ab72a11a1f7c1a01b78 * Model link: http://mobvoi-speech-public.ufile.ucloud.cn/public/wenet/librispeech/20210216_conformer_exp.tar.gz -* LM-fgbig: [4-gram.arpa.gz](http://www.openslr.org/resources/11/4-gram.arpa.gz) +* LM-fglarge: [4-gram.arpa.gz](http://www.openslr.org/resources/11/4-gram.arpa.gz) -| decoding mode | test clean | test other | -|--------------------------------|------------|------------| -| ctc greedy search | 3.51 | 9.57 | -| ctc prefix beam search | 3.51 | 9.56 | -| attention decoder | 3.05 | 8.36 | -| attention rescoring | 3.18 | 8.72 | -| attention rescoring (beam 50) | 3.12 | 8.55 | -| LM-fgbig + attention rescoring | 3.09 | 7.40 | +| decoding mode | test clean | test other | +|----------------------------------|------------|------------| +| ctc greedy search | 3.51 | 9.57 | +| ctc prefix beam search | 3.51 | 9.56 | +| attention decoder | 3.05 | 8.36 | +| attention rescoring | 3.18 | 8.72 | +| attention rescoring (beam 50) | 3.12 | 8.55 | +| LM-fglarge + attention rescoring | 3.09 | 7.40 | ## Conformer U2++ Result @@ -58,28 +64,28 @@ test other * Decoding info: ctc_weight 0.5, average_num 30 * Git hash: 90d9a559840e765e82119ab72a11a1f7c1a01b78 * Model link: http://mobvoi-speech-public.ufile.ucloud.cn/public/wenet/librispeech/20210215_unified_conformer_exp.tar.gz -* Default LM: [3-gram.pruned.1e-7.arpa.gz](http://www.openslr.org/resources/11/3-gram.pruned.1e-7.arpa.gz) -* LM-tgbig: [3-gram.arpa.gz](http://www.openslr.org/resources/11/3-gram.arpa.gz) -* LM-fgbig: [4-gram.arpa.gz](http://www.openslr.org/resources/11/4-gram.arpa.gz) +* LM-tgmed: [3-gram.pruned.1e-7.arpa.gz](http://www.openslr.org/resources/11/3-gram.pruned.1e-7.arpa.gz) +* LM-tglarge: [3-gram.arpa.gz](http://www.openslr.org/resources/11/3-gram.arpa.gz) +* LM-fglarge: [4-gram.arpa.gz](http://www.openslr.org/resources/11/4-gram.arpa.gz) test clean -| decoding mode | full | 16 | -|--------------------------------|------|------| -| ctc prefix beam search | 4.26 | 5.00 | -| attention decoder | 3.05 | 3.44 | -| attention rescoring | 3.72 | 4.10 | -| attention rescoring (beam 50) | 3.57 | 3.95 | -| LM + attention rescoring | 3.56 | 4.02 | -| LM-tgbig + attention rescoring | 3.40 | 3.82 | -| LM-fgbig + attention rescoring | 3.38 | 3.74 | +| decoding mode | full | 16 | +|----------------------------------|------|------| +| ctc prefix beam search | 4.26 | 5.00 | +| attention decoder | 3.05 | 3.44 | +| attention rescoring | 3.72 | 4.10 | +| attention rescoring (beam 50) | 3.57 | 3.95 | +| LM-tgmed + attention rescoring | 3.56 | 4.02 | +| LM-tglarge + attention rescoring | 3.40 | 3.82 | +| LM-fglarge + attention rescoring | 3.38 | 3.74 | test other -| decoding mode | full | 16 | -|--------------------------------|-------|-------| -| ctc prefix beam search | 10.87 | 12.87 | -| attention decoder | 9.07 | 10.44 | -| attention rescoring | 9.74 | 11.61 | -| attention rescoring (beam 50) | 9.34 | 11.13 | -| LM + attention rescoring | 8.78 | 10.26 | -| LM-tgbig + attention rescoring | 8.34 | 9.74 | -| LM-fgbig + attention rescoring | 8.17 | 9.44 | +| decoding mode | full | 16 | +|----------------------------------|-------|-------| +| ctc prefix beam search | 10.87 | 12.87 | +| attention decoder | 9.07 | 10.44 | +| attention rescoring | 9.74 | 11.61 | +| attention rescoring (beam 50) | 9.34 | 11.13 | +| LM-tgmed + attention rescoring | 8.78 | 10.26 | +| LM-tglarge + attention rescoring | 8.34 | 9.74 | +| LM-fglarge + attention rescoring | 8.17 | 9.44 |