├── .github └── workflows │ ├── docker-publish.yml │ └── hadolint.yml ├── .gitignore ├── Dockerfile ├── README.md ├── animate_mfcc.py ├── conf ├── mfcc.conf ├── mfcc_200fps.conf ├── mfcc_80fps.conf └── online_cmvn.conf ├── data ├── local │ └── dict │ │ ├── english_mfa_reference.dict │ │ └── lexicon_common_voice_uk.txt └── semesyuk_farshrutka_prologue │ ├── export.scp │ ├── text │ └── wav │ ├── 01_prologue-00000000-00001000-1.wav │ ├── 01_prologue-00000500-00001500-1.wav │ ├── 01_prologue-00001000-00002000-1.wav │ ├── 01_prologue-00001500-00002500-1.wav │ ├── 01_prologue-00002000-00003000-1.wav │ ├── 01_prologue-00002500-00003500-1.wav │ ├── 01_prologue-00003000-00004000-1.wav │ ├── 01_prologue-00003500-00004500-1.wav │ ├── 01_prologue-00004000-00005000-1.wav │ ├── 01_prologue-00004500-00005500-1.wav │ ├── 01_prologue-00005000-00006000-1.wav │ ├── 01_prologue-00005500-00006500-1.wav │ ├── 01_prologue-00006000-00007000-1.wav │ ├── 01_prologue-00006500-00007500-1.wav │ ├── 01_prologue-00007000-00008000-1.wav │ ├── 01_prologue-00007500-00008500-1.wav │ ├── 01_prologue-00008000-00009000-1.wav │ ├── 01_prologue-00008500-00009500-1.wav │ ├── 01_prologue-00009000-00010000-1.wav │ ├── 01_prologue-00009500-00010500-1.wav │ ├── 01_prologue-00010000-00011000-1.wav │ ├── 01_prologue-00010500-00011500-1.wav │ ├── 01_prologue-00011000-00012000-1.wav │ ├── 01_prologue-00011500-00012500-1.wav │ ├── 01_prologue-00012000-00013000-1.wav │ ├── 01_prologue-00012500-00013500-1.wav │ ├── 01_prologue-00013000-00014000-1.wav │ ├── 01_prologue-00013500-00014500-1.wav │ ├── 01_prologue-00014000-00015000-1.wav │ ├── 01_prologue-00014500-00015500-1.wav │ ├── 01_prologue-00015000-00016000-1.wav │ ├── 01_prologue-00015500-00016500-1.wav │ ├── 01_prologue-00016000-00017000-1.wav │ ├── 01_prologue-00016500-00017500-1.wav │ ├── 01_prologue-00017000-00018000-1.wav │ └── 01_prologue-00017500-00018601-1.wav ├── exp ├── bigrams.png ├── dft.png ├── dftflip.png ├── dftimag.png ├── masked_windows.png └── windows.png ├── nanoalign.py ├── nanoem.py ├── nanoframes.py ├── nanolib.py ├── nanoshow.py ├── path.sh ├── setup.py ├── steps ├── uk ├── __init__.py ├── align_utterances.py ├── clean_text.py ├── dynamic.py ├── extract_segments.py ├── g2p.py ├── nlp_uk_tokens.py ├── oggwrap.py ├── prepare_dataset.py ├── prepare_dict.py ├── prepare_lang.py ├── prepare_opusar.py ├── prepare_opusbin.py ├── segment_long_utterances.py ├── share.py ├── subprocess.py ├── textgrid.py ├── train_gmm.py └── trim_silence.py └── utils /.github/workflows/docker-publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/.github/workflows/docker-publish.yml -------------------------------------------------------------------------------- /.github/workflows/hadolint.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/.github/workflows/hadolint.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/.gitignore -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/Dockerfile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/README.md -------------------------------------------------------------------------------- /animate_mfcc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/animate_mfcc.py -------------------------------------------------------------------------------- /conf/mfcc.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/conf/mfcc.conf -------------------------------------------------------------------------------- /conf/mfcc_200fps.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/conf/mfcc_200fps.conf -------------------------------------------------------------------------------- /conf/mfcc_80fps.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/conf/mfcc_80fps.conf -------------------------------------------------------------------------------- /conf/online_cmvn.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/conf/online_cmvn.conf -------------------------------------------------------------------------------- /data/local/dict/english_mfa_reference.dict: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/local/dict/english_mfa_reference.dict -------------------------------------------------------------------------------- /data/local/dict/lexicon_common_voice_uk.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/local/dict/lexicon_common_voice_uk.txt -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/export.scp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/export.scp -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/text: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/text -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00000000-00001000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00000000-00001000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00000500-00001500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00000500-00001500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00001000-00002000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00001000-00002000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00001500-00002500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00001500-00002500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00002000-00003000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00002000-00003000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00002500-00003500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00002500-00003500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00003000-00004000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00003000-00004000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00003500-00004500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00003500-00004500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00004000-00005000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00004000-00005000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00004500-00005500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00004500-00005500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00005000-00006000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00005000-00006000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00005500-00006500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00005500-00006500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00006000-00007000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00006000-00007000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00006500-00007500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00006500-00007500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00007000-00008000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00007000-00008000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00007500-00008500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00007500-00008500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00008000-00009000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00008000-00009000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00008500-00009500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00008500-00009500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00009000-00010000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00009000-00010000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00009500-00010500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00009500-00010500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00010000-00011000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00010000-00011000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00010500-00011500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00010500-00011500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00011000-00012000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00011000-00012000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00011500-00012500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00011500-00012500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00012000-00013000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00012000-00013000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00012500-00013500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00012500-00013500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00013000-00014000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00013000-00014000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00013500-00014500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00013500-00014500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00014000-00015000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00014000-00015000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00014500-00015500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00014500-00015500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00015000-00016000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00015000-00016000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00015500-00016500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00015500-00016500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00016000-00017000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00016000-00017000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00016500-00017500-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00016500-00017500-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00017000-00018000-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00017000-00018000-1.wav -------------------------------------------------------------------------------- /data/semesyuk_farshrutka_prologue/wav/01_prologue-00017500-00018601-1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/data/semesyuk_farshrutka_prologue/wav/01_prologue-00017500-00018601-1.wav -------------------------------------------------------------------------------- /exp/bigrams.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/exp/bigrams.png -------------------------------------------------------------------------------- /exp/dft.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/exp/dft.png -------------------------------------------------------------------------------- /exp/dftflip.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/exp/dftflip.png -------------------------------------------------------------------------------- /exp/dftimag.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/exp/dftimag.png -------------------------------------------------------------------------------- /exp/masked_windows.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/exp/masked_windows.png -------------------------------------------------------------------------------- /exp/windows.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/exp/windows.png -------------------------------------------------------------------------------- /nanoalign.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/nanoalign.py -------------------------------------------------------------------------------- /nanoem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/nanoem.py -------------------------------------------------------------------------------- /nanoframes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/nanoframes.py -------------------------------------------------------------------------------- /nanolib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/nanolib.py -------------------------------------------------------------------------------- /nanoshow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/nanoshow.py -------------------------------------------------------------------------------- /path.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/path.sh -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/setup.py -------------------------------------------------------------------------------- /steps: -------------------------------------------------------------------------------- 1 | ../kaldi/egs/wsj/s5/steps -------------------------------------------------------------------------------- /uk/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /uk/align_utterances.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/align_utterances.py -------------------------------------------------------------------------------- /uk/clean_text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/clean_text.py -------------------------------------------------------------------------------- /uk/dynamic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/dynamic.py -------------------------------------------------------------------------------- /uk/extract_segments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/extract_segments.py -------------------------------------------------------------------------------- /uk/g2p.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/g2p.py -------------------------------------------------------------------------------- /uk/nlp_uk_tokens.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/nlp_uk_tokens.py -------------------------------------------------------------------------------- /uk/oggwrap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/oggwrap.py -------------------------------------------------------------------------------- /uk/prepare_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/prepare_dataset.py -------------------------------------------------------------------------------- /uk/prepare_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/prepare_dict.py -------------------------------------------------------------------------------- /uk/prepare_lang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/prepare_lang.py -------------------------------------------------------------------------------- /uk/prepare_opusar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/prepare_opusar.py -------------------------------------------------------------------------------- /uk/prepare_opusbin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/prepare_opusbin.py -------------------------------------------------------------------------------- /uk/segment_long_utterances.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/segment_long_utterances.py -------------------------------------------------------------------------------- /uk/share.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/share.py -------------------------------------------------------------------------------- /uk/subprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/subprocess.py -------------------------------------------------------------------------------- /uk/textgrid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/textgrid.py -------------------------------------------------------------------------------- /uk/train_gmm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/train_gmm.py -------------------------------------------------------------------------------- /uk/trim_silence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/proger/uk/HEAD/uk/trim_silence.py -------------------------------------------------------------------------------- /utils: -------------------------------------------------------------------------------- 1 | ../kaldi/egs/wsj/s5/utils --------------------------------------------------------------------------------