-
Notifications
You must be signed in to change notification settings - Fork 33
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
cmp files not genereted #1
Comments
Please let me see the output when you do:
ls /root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/align_lab
ls /root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/cmp
Regards,
Oliver
On 24 Aug 2017, at 14:18, Yunchao He ***@***.***> wrote:
/root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/align_lab and /root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/cmp
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
|
Also, please try starting from scratch:
rm -r $OSSIAN/train/rm/speakers/rss_toy_demo/naive_01_nn/
$OSSIAN/voices/rm/rss_toy_demo/naive_01_nn/
And running train.py again as before.
Quoting Yunchao He <notifications@github.com> on Thu, 24 Aug 2017
13:18:52 +0000 (UTC):
… I try to run the `rss_toy_demo` example step by step according to
the `README.md`. However, I get errors when execute `python
./scripts/train.py -s rss_toy_demo -l rm naive_01_nn`. I dig into
the code, found that there is no `*.cmp` files under
`/train//rm/speakers/rss_toy_demo/naive_01_nn/cmp/` folder.
Could anyone tell me why? And how to generate these files?
https://github.com/CSTR-Edinburgh/Ossian/blob/114ebc7eb94ab8251bd73f62799b204424efb133/scripts/acoustic_model_training/steps/set_up_data.py#L70
Here is the detail info:
```
***@***.***:~/workspace/Projects/Ossian#
python ./scripts/train.py -s rss_toy_demo -l rm naive_01_nn
-- Gather corpus
-- Train voice
/root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn
/root/workspace/Projects/Ossian/voices//rm/rss_toy_demo/naive_01_nn
try loading config from python...
/root/workspace/Projects/Ossian/recipes/naive_01_nn.cfg
{'state_contexts': [('start_time', './attribute::start'),
('end_time', './attribute::end'), ('htk_state',
'count(./preceding-sibling::state) + 1'), ('htk_monophone',
'./ancestor::segment/attribute::pronunciation'), ('ll_segment',
'./ancestor::segment/preceding::segment[2]/attribute::pronunciation'),
('l_segment',
'./ancestor::segment/preceding::segment[1]/attribute::pronunciation'),
('c_segment', './ancestor::segment/attribute::pronunciation'),
('r_segment',
'./ancestor::segment/following::segment[1]/attribute::pronunciation'),
('rr_segment',
'./ancestor::segment/following::segment[2]/attribute::pronunciation'),
('length_left_word',
***@***.***_class='word'][1]/descendant::segment)"), ('length_current_word', 'count(ancestor::token/descendant::segment)'), ('length_right_word', ***@***.***_class='word'][1]/descendant::segment)"), ('since_beginning_of_word', "count_Xs_since_start_Y('segment', 'token')"), ('till_end_of_word', "count_Xs_till_end_Y('segment', 'token')"), ('length_l_phrase_in_words', ***@***.***_class='word'])"), ('length_c_phrase_in_words', ***@***.***_class='word'])"), ('length_r_phrase_in_words', ***@***.***_class='word'])"), ('length_l_phrase_in_segments', 'count(ancestor::phrase/preceding::phrase[1]/descendant::segment)'), ('length_c_phrase_in_segments', 'count(ancestor::phrase/descendant::segment)'), ('length_r_phrase_in_segments', 'count(ancestor::phrase/following::phrase[1]/descendant::segment)'), ('since_phrase_start_in_segs', "count_Xs_since_start_Y('segment', 'phrase')"), ('till_phrase_end_in_segs', "count_Xs_till_end_Y('segment', 'phrase')"), ('since_phrase_start_in_words', ***@***.***_class="word"]\', \'phrase\')'), ('till_phrase_end_in_words', ***@***.***_class="word"]\', \'phrase\')'), ('since_start_sentence_in_segments', "count_Xs_since_start_Y('segment', 'utt')"), ('since_start_sentence_in_words', ***@***.***_class="word"]\', \'utt\')'), ('since_start_sentence_in_phrases', "count_Xs_since_start_Y('phrase', 'utt')"), ('till_end_sentence_in_segments', "count_Xs_till_end_Y('segment', 'utt')"), ('till_end_sentence_in_words', ***@***.***_class="word"]\', \'utt\')'), ('till_end_sentence_in_phrases', "count_Xs_till_end_Y('phrase', 'utt')"), ('length_sentence_in_segments', 'count(ancestor::utt/descendant::segment)'), ('length_sentence_in_words', ***@***.***_class='word'])"), ('length_sentence_in_phrases', 'count(ancestor::utt/descendant::phrase)'), ('L_vsm_d1', ***@***.***_class='word'][1]/attribute::vsm_d1"), ('C_vsm_d1', './ancestor::token/attribute::vsm_d1'), ('R_vsm_d1', ***@***.***_class='word'][1]/attribute::vsm_d1"), ('L_vsm_d2', ***@***.***_class='word'][1]/attribute::vsm_d2"), ('C_vsm_d2', './ancestor::token/attribute::vsm_d2'), ('R_vsm_d2', ***@***.***_class='word'][1]/attribute::vsm_d2"), ('L_vsm_d3', ***@***.***_class='word'][1]/attribute::vsm_d3"), ('C_vsm_d3', './ancestor::token/attribute::vsm_d3'), ('R_vsm_d3', ***@***.***_class='word'][1]/attribute::vsm_d3"), ('L_vsm_d4', ***@***.***_class='word'][1]/attribute::vsm_d4"), ('C_vsm_d4', './ancestor::token/attribute::vsm_d4'), ('R_vsm_d4', ***@***.***_class='word'][1]/attribute::vsm_d4"), ('L_vsm_d5', ***@***.***_class='word'][1]/attribute::vsm_d5"), ('C_vsm_d5', './ancestor::token/attribute::vsm_d5'), ('R_vsm_d5', ***@***.***_class='word'][1]/attribute::vsm_d5"), ('L_vsm_d6', ***@***.***_class='word'][1]/attribute::vsm_d6"), ('C_vsm_d6', './ancestor::token/attribute::vsm_d6'), ('R_vsm_d6', ***@***.***_class='word'][1]/attribute::vsm_d6"), ('L_vsm_d7', ***@***.***_class='word'][1]/attribute::vsm_d7"), ('C_vsm_d7', './ancestor::token/attribute::vsm_d7'), ('R_vsm_d7', ***@***.***_class='word'][1]/attribute::vsm_d7"), ('L_vsm_d8', ***@***.***_class='word'][1]/attribute::vsm_d8"), ('C_vsm_d8', './ancestor::token/attribute::vsm_d8'), ('R_vsm_d8', ***@***.***_class='word'][1]/attribute::vsm_d8"), ('L_vsm_d9', ***@***.***_class='word'][1]/attribute::vsm_d9"), ('C_vsm_d9', './ancestor::token/attribute::vsm_d9'), ('R_vsm_d9', ***@***.***_class='word'][1]/attribute::vsm_d9"), ('L_vsm_d10', ***@***.***_class='word'][1]/attribute::vsm_d10"), ('C_vsm_d10', './ancestor::token/attribute::vsm_d10'), ('R_vsm_d10', ***@***.***_class='word'][1]/attribute::vsm_d10")], 'dur_label_maker': <FeatureDumper.FeatureDumper object at 0x7fd779ceb6d0>, 'SKLDecisionTreePausePredictor': <class 'SKLProcessors.SKLDecisionTreePausePredictor'>, 'train_stages': [[<Tokenisers.RegexTokeniser object at 0x7fd77a645b90>, <Phonetisers.NaivePhonetiser object at 0x7fd779cd5d50>, <VSMTagger.VSMTagger object at 0x7fd779ceb710>], [<FeatureDumper.FeatureDumper object at 0x7fd779ceb790>, <FeatureExtractor.WorldExtractor object at 0x7fd779ceb510>, <Aligner.StateAligner object at 0x7fd779ceb590>, <SKLProcessors.SKLDecisionTreePausePredictor object at 0x7fd779ceb610>, <PhraseMaker.PhraseMaker object at 0x7fd779ceb7d0>, <FeatureDumper.FeatureDumper object at 0x7fd779ceb690>], [<FeatureDumper.FeatureDumper object at 0x7fd779ceb6d0>, <NN.NNDurationPredictor object at 0x7fd77ea2bb50>, <FeatureDumper.FeatureDumper object at 0x7fd779cd5d90>, <NN.NNAcousticPredictor object at 0x7fd779cd5ed0>]], 'PUNC_PATT': '[\\p{C}||\\p{P}||\\p{S}]', 'JUNCTURE_NODES': ***@***.***_class='space'] | ***@***.***_class='punctuation']", 'WorldExtractor': <class 'FeatureExtractor.WorldExtractor'>, 'RegexTokeniser': <class 'Tokenisers.RegexTokeniser'>, 'current_dir': '/root/workspace/Projects/Ossian/recipes', 'phrase_adder': <PhraseMaker.PhraseMaker object at 0x7fd779ceb7d0>, 'dur_data_maker': <FeatureDumper.FeatureDumper object at 0x7fd779ceb690>, 'pause_predictor': <SKLProcessors.SKLDecisionTreePausePredictor object at 0x7fd779ceb610>, 'speech_generation': [<FeatureDumper.FeatureDumper object at 0x7fd779ceb6d0>, <NN.NNDurationPredictor object at 0x7fd77ea2bb50>, <FeatureDumper.FeatureDumper object at 0x7fd779cd5d90>, <NN.NNAcousticPredictor object at 0x7fd779cd5ed0>], 'runtime_stages': [[<Tokenisers.RegexTokeniser object at 0x7fd77a645b90>, <Phonetisers.NaivePhonetiser object at 0x7fd779cd5d50>, <VSMTagger.VSMTagger object at 0x7fd779ceb710>], [<SKLProcessors.SKLDecisionTreePausePredictor object at 0x7fd779ceb610>, <PhraseMaker.PhraseMaker object at 0x7fd779ceb7d0>], [<FeatureDumper.FeatureDumper object at 0x7fd779ceb6d0>, <NN.NNDurationPredictor object at 0x7fd77ea2bb50>, <FeatureDumper.FeatureDumper object at 0x7fd779cd5d90>, <NN.NNAcousticPredictor object at 0x7fd779cd5ed0>]], 'text_proc': [<Tokenisers.RegexTokeniser object at 0x7fd77a645b90>, <Phonetisers.NaivePhonetiser object at 0x7fd779cd5d50>, <VSMTagger.VSMTagger object at 0x7fd779ceb710>], 'acoustic_predictor': <NN.NNAcousticPredictor object at 0x7fd779cd5ed0>, 'duration_predictor': <NN.NNDurationPredictor object at 0x7fd77ea2bb50>, 'NNAcousticPredictor': <class 'NN.NNAcousticPredictor'>, 'align_label_dumper': <FeatureDumper.FeatureDumper object at 0x7fd779ceb790>, 'pause_predictor_features': [('response', './attribute::has_silence="yes"'), ('token_is_punctuation', './attribute::token_class="punctuation"'), ('since_start_utterance_in_words', ***@***.***_class='word'])"), ('till_end_utterance_in_words', ***@***.***_class='word'])"), ('L_vsm_d1', ***@***.***_class='word'][1]/attribute::vsm_d1"), ('C_vsm_d1', './attribute::vsm_d1'), ('R_vsm_d1', ***@***.***_class='word'][1]/attribute::vsm_d1"), ('L_vsm_d2', ***@***.***_class='word'][1]/attribute::vsm_d2"), ('C_vsm_d2', './attribute::vsm_d2'), ('R_vsm_d2', ***@***.***_class='word'][1]/attribute::vsm_d2"), ('L_vsm_d3', ***@***.***_class='word'][1]/attribute::vsm_d3"), ('C_vsm_d3', './attribute::vsm_d3'), ('R_vsm_d3', ***@***.***_class='word'][1]/attribute::vsm_d3"), ('L_vsm_d4', ***@***.***_class='word'][1]/attribute::vsm_d4"), ('C_vsm_d4', './attribute::vsm_d4'), ('R_vsm_d4', ***@***.***_class='word'][1]/attribute::vsm_d4"), ('L_vsm_d5', ***@***.***_class='word'][1]/attribute::vsm_d5"), ('C_vsm_d5', './attribute::vsm_d5'), ('R_vsm_d5', ***@***.***_class='word'][1]/attribute::vsm_d5"), ('L_vsm_d6', ***@***.***_class='word'][1]/attribute::vsm_d6"), ('C_vsm_d6', './attribute::vsm_d6'), ('R_vsm_d6', ***@***.***_class='word'][1]/attribute::vsm_d6"), ('L_vsm_d7', ***@***.***_class='word'][1]/attribute::vsm_d7"), ('C_vsm_d7', './attribute::vsm_d7'), ('R_vsm_d7', ***@***.***_class='word'][1]/attribute::vsm_d7"), ('L_vsm_d8', ***@***.***_class='word'][1]/attribute::vsm_d8"), ('C_vsm_d8', './attribute::vsm_d8'), ('R_vsm_d8', ***@***.***_class='word'][1]/attribute::vsm_d8"), ('L_vsm_d9', ***@***.***_class='word'][1]/attribute::vsm_d9"), ('C_vsm_d9', './attribute::vsm_d9'), ('R_vsm_d9', ***@***.***_class='word'][1]/attribute::vsm_d9"), ('L_vsm_d10', ***@***.***_class='word'][1]/attribute::vsm_d10"), ('C_vsm_d10', './attribute::vsm_d10'), ('R_vsm_d10', ***@***.***_class='word'][1]/attribute::vsm_d10")], 'PhraseMaker': <class 'PhraseMaker.PhraseMaker'>, 'alignment': [<FeatureDumper.FeatureDumper object at 0x7fd779ceb790>, <FeatureExtractor.WorldExtractor object at 0x7fd779ceb510>, <Aligner.StateAligner object at 0x7fd779ceb590>, <SKLProcessors.SKLDecisionTreePausePredictor object at 0x7fd779ceb610>, <PhraseMaker.PhraseMaker object at 0x7fd779ceb7d0>, <FeatureDumper.FeatureDumper object at 0x7fd779ceb690>], 'VSMTagger': <class 'VSMTagger.VSMTagger'>, 'duration_data_contexts': [('state_1_nframes', '(./state[1]/attribute::end - ./state[1]/attribute::start) div 5'), ('state_2_nframes', '(./state[2]/attribute::end - ./state[2]/attribute::start) div 5'), ('state_3_nframes', '(./state[3]/attribute::end - ./state[3]/attribute::start) div 5'), ('state_4_nframes', '(./state[4]/attribute::end - ./state[4]/attribute::start) div 5'), ('state_5_nframes', '(./state[5]/attribute::end - ./state[5]/attribute::start) div 5')], 'phone_and_state_contexts': [('length_left_word', ***@***.***_class='word'][1]/descendant::segment)"), ('length_current_word', 'count(ancestor::token/descendant::segment)'), ('length_right_word', ***@***.***_class='word'][1]/descendant::segment)"), ('since_beginning_of_word', "count_Xs_since_start_Y('segment', 'token')"), ('till_end_of_word', "count_Xs_till_end_Y('segment', 'token')"), ('length_l_phrase_in_words', ***@***.***_class='word'])"), ('length_c_phrase_in_words', ***@***.***_class='word'])"), ('length_r_phrase_in_words', ***@***.***_class='word'])"), ('length_l_phrase_in_segments', 'count(ancestor::phrase/preceding::phrase[1]/descendant::segment)'), ('length_c_phrase_in_segments', 'count(ancestor::phrase/descendant::segment)'), ('length_r_phrase_in_segments', 'count(ancestor::phrase/following::phrase[1]/descendant::segment)'), ('since_phrase_start_in_segs', "count_Xs_since_start_Y('segment', 'phrase')"), ('till_phrase_end_in_segs', "count_Xs_till_end_Y('segment', 'phrase')"), ('since_phrase_start_in_words', ***@***.***_class="word"]\', \'phrase\')'), ('till_phrase_end_in_words', ***@***.***_class="word"]\', \'phrase\')'), ('since_start_sentence_in_segments', "count_Xs_since_start_Y('segment', 'utt')"), ('since_start_sentence_in_words', ***@***.***_class="word"]\', \'utt\')'), ('since_start_sentence_in_phrases', "count_Xs_since_start_Y('phrase', 'utt')"), ('till_end_sentence_in_segments', "count_Xs_till_end_Y('segment', 'utt')"), ('till_end_sentence_in_words', ***@***.***_class="word"]\', \'utt\')'), ('till_end_sentence_in_phrases', "count_Xs_till_end_Y('phrase', 'utt')"), ('length_sentence_in_segments', 'count(ancestor::utt/descendant::segment)'), ('length_sentence_in_words', ***@***.***_class='word'])"), ('length_sentence_in_phrases', 'count(ancestor::utt/descendant::phrase)'), ('L_vsm_d1', ***@***.***_class='word'][1]/attribute::vsm_d1"), ('C_vsm_d1', './ancestor::token/attribute::vsm_d1'), ('R_vsm_d1', ***@***.***_class='word'][1]/attribute::vsm_d1"), ('L_vsm_d2', ***@***.***_class='word'][1]/attribute::vsm_d2"), ('C_vsm_d2', './ancestor::token/attribute::vsm_d2'), ('R_vsm_d2', ***@***.***_class='word'][1]/attribute::vsm_d2"), ('L_vsm_d3', ***@***.***_class='word'][1]/attribute::vsm_d3"), ('C_vsm_d3', './ancestor::token/attribute::vsm_d3'), ('R_vsm_d3', ***@***.***_class='word'][1]/attribute::vsm_d3"), ('L_vsm_d4', ***@***.***_class='word'][1]/attribute::vsm_d4"), ('C_vsm_d4', './ancestor::token/attribute::vsm_d4'), ('R_vsm_d4', ***@***.***_class='word'][1]/attribute::vsm_d4"), ('L_vsm_d5', ***@***.***_class='word'][1]/attribute::vsm_d5"), ('C_vsm_d5', './ancestor::token/attribute::vsm_d5'), ('R_vsm_d5', ***@***.***_class='word'][1]/attribute::vsm_d5"), ('L_vsm_d6', ***@***.***_class='word'][1]/attribute::vsm_d6"), ('C_vsm_d6', './ancestor::token/attribute::vsm_d6'), ('R_vsm_d6', ***@***.***_class='word'][1]/attribute::vsm_d6"), ('L_vsm_d7', ***@***.***_class='word'][1]/attribute::vsm_d7"), ('C_vsm_d7', './ancestor::token/attribute::vsm_d7'), ('R_vsm_d7', ***@***.***_class='word'][1]/attribute::vsm_d7"), ('L_vsm_d8', ***@***.***_class='word'][1]/attribute::vsm_d8"), ('C_vsm_d8', './ancestor::token/attribute::vsm_d8'), ('R_vsm_d8', ***@***.***_class='word'][1]/attribute::vsm_d8"), ('L_vsm_d9', ***@***.***_class='word'][1]/attribute::vsm_d9"), ('C_vsm_d9', './ancestor::token/attribute::vsm_d9'), ('R_vsm_d9', ***@***.***_class='word'][1]/attribute::vsm_d9"), ('L_vsm_d10', ***@***.***_class='word'][1]/attribute::vsm_d10"), ('C_vsm_d10', './ancestor::token/attribute::vsm_d10'), ('R_vsm_d10', ***@***.***_class='word'][1]/attribute::vsm_d10")], 'word_vector_tagger': <VSMTagger.VSMTagger object at 0x7fd779ceb710>, 'inspect': <module 'inspect' from '/usr/lib/python2.7/inspect.pyc'>, 'tokenisation_pattern': '(\\p{Z}*[\\p{C}||\\p{P}||\\p{S}]*\\p{Z}+|\\p{Z}*[\\p{C}||\\p{P}||\\p{S}]+\\Z)', 'aligner': <Aligner.StateAligner object at 0x7fd779ceb590>, 'sys': <module 'sys' (built-in)>, 'dnn_label_maker': <FeatureDumper.FeatureDumper object at 0x7fd779cd5d90>, 'NaivePhonetiser': <class 'Phonetisers.NaivePhonetiser'>, 'tokeniser': <Tokenisers.RegexTokeniser object at 0x7fd77a645b90>, 'LETTER_PATT': '[\\p{L}||\\p{N}||\\p{M}]', 'AcousticModelWorld': <class 'AcousticModel.AcousticModelWorld'>, 'speech_feature_extractor': <FeatureExtractor.WorldExtractor object at 0x7fd779ceb510>, 'dim': 10, 'c': <module 'default.const' from '/root/workspace/Projects/Ossian/scripts/default/const.pyc'>, 'FeatureDumper': <class 'FeatureDumper.FeatureDumper'>, 'word_vsm_dim': 10, 'speech_coding_config': {'delta_delta_window': '1.0 -2.0 1.0', 'static_window': '1', 'order': 59, 'delta_window': '-0.5 0.0 0.5'}, 'pause_prediction': [<SKLProcessors.SKLDecisionTreePausePredictor object at 0x7fd779ceb610>, <PhraseMaker.PhraseMaker object at 0x7fd779ceb7d0>], 'i': 5, 'SPACE_PATT': '\\p{Z}', 'PUNC_OR_SPACE_PATT': '[\\p{Z}||\\p{C}||\\p{P}||\\p{S}]', 'phonetiser': <Phonetisers.NaivePhonetiser object at 0x7fd779cd5d50>, 'NNDurationPredictor': <class 'NN.NNDurationPredictor'>, 'os': <module 'os' from '/usr/lib/python2.7/os.pyc'>, 'phone_contexts': [('htk_monophone', './attribute::pronunciation'), ('start_time', './attribute::start'), ('end_time', './attribute::end'), ('ll_segment', 'preceding::segment[2]/attribute::pronunciation'), ('l_segment', 'preceding::segment[1]/attribute::pronunciation'), ('c_segment', './attribute::pronunciation'), ('r_segment', 'following::segment[1]/attribute::pronunciation'), ('rr_segment', 'following::segment[2]/attribute::pronunciation'), ('length_left_word', ***@***.***_class='word'][1]/descendant::segment)"), ('length_current_word', 'count(ancestor::token/descendant::segment)'), ('length_right_word', ***@***.***_class='word'][1]/descendant::segment)"), ('since_beginning_of_word', "count_Xs_since_start_Y('segment', 'token')"), ('till_end_of_word', "count_Xs_till_end_Y('segment', 'token')"), ('length_l_phrase_in_words', ***@***.***_class='word'])"), ('length_c_phrase_in_words', ***@***.***_class='word'])"), ('length_r_phrase_in_words', ***@***.***_class='word'])"), ('length_l_phrase_in_segments', 'count(ancestor::phrase/preceding::phrase[1]/descendant::segment)'), ('length_c_phrase_in_segments', 'count(ancestor::phrase/descendant::segment)'), ('length_r_phrase_in_segments', 'count(ancestor::phrase/following::phrase[1]/descendant::segment)'), ('since_phrase_start_in_segs', "count_Xs_since_start_Y('segment', 'phrase')"), ('till_phrase_end_in_segs', "count_Xs_till_end_Y('segment', 'phrase')"), ('since_phrase_start_in_words', ***@***.***_class="word"]\', \'phrase\')'), ('till_phrase_end_in_words', ***@***.***_class="word"]\', \'phrase\')'), ('since_start_sentence_in_segments', "count_Xs_since_start_Y('segment', 'utt')"), ('since_start_sentence_in_words', ***@***.***_class="word"]\', \'utt\')'), ('since_start_sentence_in_phrases', "count_Xs_since_start_Y('phrase', 'utt')"), ('till_end_sentence_in_segments', "count_Xs_till_end_Y('segment', 'utt')"), ('till_end_sentence_in_words', ***@***.***_class="word"]\', \'utt\')'), ('till_end_sentence_in_phrases', "count_Xs_till_end_Y('phrase', 'utt')"), ('length_sentence_in_segments', 'count(ancestor::utt/descendant::segment)'), ('length_sentence_in_words', ***@***.***_class='word'])"), ('length_sentence_in_phrases', 'count(ancestor::utt/descendant::phrase)'), ('L_vsm_d1', ***@***.***_class='word'][1]/attribute::vsm_d1"), ('C_vsm_d1', './ancestor::token/attribute::vsm_d1'), ('R_vsm_d1', ***@***.***_class='word'][1]/attribute::vsm_d1"), ('L_vsm_d2', ***@***.***_class='word'][1]/attribute::vsm_d2"), ('C_vsm_d2', './ancestor::token/attribute::vsm_d2'), ('R_vsm_d2', ***@***.***_class='word'][1]/attribute::vsm_d2"), ('L_vsm_d3', ***@***.***_class='word'][1]/attribute::vsm_d3"), ('C_vsm_d3', './ancestor::token/attribute::vsm_d3'), ('R_vsm_d3', ***@***.***_class='word'][1]/attribute::vsm_d3"), ('L_vsm_d4', ***@***.***_class='word'][1]/attribute::vsm_d4"), ('C_vsm_d4', './ancestor::token/attribute::vsm_d4'), ('R_vsm_d4', ***@***.***_class='word'][1]/attribute::vsm_d4"), ('L_vsm_d5', ***@***.***_class='word'][1]/attribute::vsm_d5"), ('C_vsm_d5', './ancestor::token/attribute::vsm_d5'), ('R_vsm_d5', ***@***.***_class='word'][1]/attribute::vsm_d5"), ('L_vsm_d6', ***@***.***_class='word'][1]/attribute::vsm_d6"), ('C_vsm_d6', './ancestor::token/attribute::vsm_d6'), ('R_vsm_d6', ***@***.***_class='word'][1]/attribute::vsm_d6"), ('L_vsm_d7', ***@***.***_class='word'][1]/attribute::vsm_d7"), ('C_vsm_d7', './ancestor::token/attribute::vsm_d7'), ('R_vsm_d7', ***@***.***_class='word'][1]/attribute::vsm_d7"), ('L_vsm_d8', ***@***.***_class='word'][1]/attribute::vsm_d8"), ('C_vsm_d8', './ancestor::token/attribute::vsm_d8'), ('R_vsm_d8', ***@***.***_class='word'][1]/attribute::vsm_d8"), ('L_vsm_d9', ***@***.***_class='word'][1]/attribute::vsm_d9"), ('C_vsm_d9', './ancestor::token/attribute::vsm_d9'), ('R_vsm_d9', ***@***.***_class='word'][1]/attribute::vsm_d9"), ('L_vsm_d10', ***@***.***_class='word'][1]/attribute::vsm_d10"), ('C_vsm_d10', './ancestor::token/attribute::vsm_d10'), ('R_vsm_d10', ***@***.***_class='word'][1]/attribute::vsm_d10")], 'StateAligner': <class
'Aligner.StateAligner'>}
train
Cannot load NN model from model_dir:
/root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/processors/duration_predictor -- not trained
yet
Cannot load NN model from model_dir:
/root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/processors/acoustic_predictor -- not trained
yet
== Train voice (proc no. 1 (word_splitter)) ==
Train processor word_splitter
RegexTokeniser requires no training
Applying processor word_splitter
uuuuuuuuuuuuuuuuuuuuuuuuuuuuu
== Train voice (proc no. 2 (segment_adder)) ==
Train processor segment_adder
NaivePhonetiser requires no training
Applying processor segment_adder
uuuuuuuuuuuuuuuuuuuuuuuuuuuuu
== Train voice (proc no. 3 (word_vector_tagger)) ==
Applying processor word_vector_tagger
u u u u u u u u u u u u u u u u u u u u u u u u u u u u u
== Train voice (proc no. 4 (feature_dumper)) ==
Train processor feature_dumper
FeatureDumper already trained -- questions exist:
/root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn//SomeFileName
Applying processor feature_dumper
uuuuuuuuuuuuuuuuuuuuuuuuuuuuu
== Train voice (proc no. 5 (acoustic_feature_extractor)) ==
Train processor acoustic_feature_extractor
Applying processor acoustic_feature_extractor
uuuuuuuuuuuuuuuuuuuuuuuuuuuuu
== Train voice (proc no. 6 (aligner)) ==
Train processor aligner
Training aligner -- see
/root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/processors/aligner/training/log.txt
set_up_data.py: No matching data files found in
/root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/align_lab and
/root/workspace/Projects/Ossian/train//rm/speakers/rss_toy_demo/naive_01_nn/cmp
Aligner training failed
```
Thanks very much.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
#1
--
zzz
--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
|
Thanks very much for your reply. @oliverwatts The content of the two folders is pasted at the end. And the current Then, I tried to start from scratch. I removed the
Train:
Here is the screen info when execute this command:
The content of the two folders:
Folder Structure:
|
Please attach or mail me your version of the file: train/rm/speakers/rss_toy_demo/naive_01_nn/cmp/adr_diph1_001.bap.double |
Here is just the And all the files in this folder is here: naive_01_nn_cmp_folder.tar.gz Thanks. |
It seems that the call to x2x at line 203 of Ossian/scripts/processors/FeatureExtractor.py gave a non-zero exit code, even though the data produced seems fine. Please comment out these lines at 203ff:
and replace with:
The same might be necessary with other calls to x2x at lines 211, 218 and 232. Then clean up:
and try again, turning parallelisation off with flag
Let me know if this runs OK, and please paste output here. |
Thanks. According to your advice, I analysed each system command called by Thanks again. |
Commit f071281 addresses this by checking that the necessary executables are in place. |
I try to run the
rss_toy_demo
example step by step according to theREADME.md
. However, I get errors when executepython ./scripts/train.py -s rss_toy_demo -l rm naive_01_nn
. I dig into the code, found that there is no*.cmp
files under/train//rm/speakers/rss_toy_demo/naive_01_nn/cmp/
folder.Could anyone tell me why? And how to generate these files?
Ossian/scripts/acoustic_model_training/steps/set_up_data.py
Line 70 in 114ebc7
Here is the detail info:
Thanks very much.
The text was updated successfully, but these errors were encountered: