German

Nested
New 30k words 200 hours german models released
User: guenter
Date: 11/25/2016 5:23 pm
Views: 7723
Rating: 1

Just uploaded the latest 20161117 release of the german voxforge models to

http://goofy.zamia.org/voxforge/de/

in addition to previous releases this one covers most of the german-speechdata-package-v2.tar.gz - all in all over 200 hours of material.

Also, there are new model types in this release:

  • a PTM model for CMU Sphinx (for mobile use)
  • two nnet3 models for kaldi-asr (great accuracy and online decoding support)
    if you're interested in using those from python code, check out my python kaldi wrapper here: 
    https://github.com/gooofy/py-kaldi-simple 

 

stats:


30684 lexicon entries.
total duration of all good submissions: 214:55:02
CMU Sphinx Models:
cmusphinx cont model: SENTENCE ERROR: 25.4% (1523/6006)   WORD ERROR RATE: 5.7% (4147/73022)
cmusphinx ptm model: SENTENCE ERROR: 24.7% (1481/6006)   WORD ERROR RATE: 7.1% (5199/73022)
kaldi gmm models: 
%WER 8.34 [ 6090 / 73007, 994 ins, 1306 del, 3790 sub ] exp/tri3b/decode.si/wer_16
%WER 7.39 [ 5397 / 73007, 634 ins, 1611 del, 3152 sub ] exp/tri2b/decode/wer_18
%WER 5.70 [ 4165 / 73007, 397 ins, 1204 del, 2564 sub ] exp/tri3b_mpe/decode/wer_17
%WER 5.46 [ 3989 / 73007, 384 ins, 1110 del, 2495 sub ] exp/tri3b_mmi/decode/wer_13
%WER 5.29 [ 3862 / 73007, 475 ins, 1044 del, 2343 sub ] exp/tri2b_mpe/decode/wer_16
%WER 5.29 [ 3861 / 73007, 324 ins, 1207 del, 2330 sub ] exp/tri3b_mmi_b0.05/decode/wer_15
%WER 4.95 [ 3611 / 73007, 646 ins, 924 del, 2041 sub ] exp/tri3b/decode/wer_17
%WER 4.23 [ 3090 / 73007, 352 ins, 767 del, 1971 sub ] exp/tri2b_mmi/decode/wer_12
%WER 4.16 [ 3035 / 73007, 333 ins, 804 del, 1898 sub ] exp/tri2b_mmi_b0.05/decode/wer_13
kaldi nnet3 models: 
%WER 1.52 [ 1112 / 73007, 192 ins, 314 del, 606 sub ] exp/nnet3/nnet_tdnn_a/decode/wer_11_0.0
%WER 1.33 [ 972 / 73007, 175 ins, 252 del, 545 sub ] exp/nnet3/lstm_ld5/decode/wer_11_0.0
sequitur g2p model:
    total: 3069 strings, 36060 symbols
    successfully translated: 3068 (99.97%) strings, 36060 (100.00%) symbols
        string errors:       1261 (41.10%)
        symbol errors:       2831 (7.85%)
            insertions:      969 (2.69%)
            deletions:       962 (2.67%)
            substitutions:   900 (2.50%)
    translation failed:      1 (0.03%) strings, 0 (0.00%) symbols
    total string errors:     1262 (41.12%)
    total symbol errors:     2831 (7.85%)


Re: New 30k words 200 hours german models released
User: guenter
Date: 4/20/2017 4:41 pm
Views: 2632
Rating: 1

r20170420 is now available:

http://goofy.zamia.org/voxforge/de/

besides covering the latest voxforge submissions, this is mainly a bugfix release. The CMU Sphinx models are based on the same srilm language model as the kaldi models now.

stats:

kaldi nnet3:
%WER 1.67 [ 1199 / 71994, 211 ins, 319 del, 669 sub ] exp/nnet3/nnet_tdnn_a/decode/wer_12_0.0
kaldi gmm:
%WER 8.35 [ 6011 / 71994, 975 ins, 1224 del, 3812 sub ] exp/tri3b/decode.si/wer_16_0.0
%WER 7.54 [ 5426 / 71994, 663 ins, 1613 del, 3150 sub ] exp/tri2b/decode/wer_16_0.0
%WER 5.63 [ 4053 / 71994, 422 ins, 1038 del, 2593 sub ] exp/tri3b_mpe/decode/wer_17_0.0
%WER 5.16 [ 3718 / 71994, 702 ins, 870 del, 2146 sub ] exp/tri3b/decode/wer_17_0.0
%WER 5.16 [ 3716 / 71994, 364 ins, 979 del, 2373 sub ] exp/tri3b_mmi/decode/wer_13_0.0
%WER 5.14 [ 3704 / 71994, 439 ins, 1021 del, 2244 sub ] exp/tri2b_mpe/decode/wer_17_0.0
%WER 5.05 [ 3639 / 71994, 366 ins, 977 del, 2296 sub ] exp/tri3b_mmi_b0.05/decode/wer_13_0.0
%WER 4.18 [ 3006 / 71994, 277 ins, 830 del, 1899 sub ] exp/tri2b_mmi/decode/wer_13_0.0
%WER 4.07 [ 2933 / 71994, 275 ins, 797 del, 1861 sub ] exp/tri2b_mmi_b0.05/decode/wer_13_0.0
CMU Sphinx Cont:
SENTENCE ERROR: 28.0% (1689/6025)   WORD ERROR RATE: 6.5% (4673/72017)
CMU Sphinx PTM:
SENTENCE ERROR: 29.3% (1768/6025)   WORD ERROR RATE: 8.6% (6222/72017)
sequitur:
    total: 3097 strings, 36758 symbols
    successfully translated: 3097 (100.00%) strings, 36758 (100.00%) symbols
        string errors:       1302 (42.04%)
        symbol errors:       2915 (7.93%)
            insertions:      1040 (2.83%)
            deletions:       954 (2.60%)
            substitutions:   921 (2.51%)
    translation failed:      0 (0.00%) strings, 0 (0.00%) symbols
    total string errors:     1302 (42.04%)
    total symbol errors:     2915 (7.93%)
PreviousNext