├── .gitignore ├── README.md ├── egs └── aishell │ ├── cmd.sh │ ├── conf │ └── fbank.conf │ ├── figures │ ├── train-k0.2-bf15000-shuffle-ls0.1-lr.png │ └── train-k0.2-bf15000-shuffle-ls0.1.png │ ├── local │ ├── aishell_data_prep.sh │ └── score.sh │ ├── path.sh │ └── run.sh ├── requirements.txt ├── src ├── __init__.py ├── bin │ ├── recognize.py │ └── train.py ├── data │ ├── __init__.py │ └── data.py ├── solver │ ├── __init__.py │ └── solver.py ├── transformer │ ├── __init__.py │ ├── attention.py │ ├── decoder.py │ ├── encoder.py │ ├── loss.py │ ├── module.py │ ├── optimizer.py │ └── transformer.py └── utils │ ├── __init__.py │ ├── data2json.sh │ ├── dump.sh │ ├── filt.py │ ├── json2trn.py │ ├── mergejson.py │ ├── scp2json.py │ ├── text2token.py │ └── utils.py ├── test ├── data │ ├── data.json │ └── train_nodup_sp_units.txt ├── learn_pytorch.py ├── learn_visdom.py ├── path.sh ├── test_data.py └── test_decode.py └── tools ├── Makefile └── kaldi-io-for-python.tar.gz /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/README.md -------------------------------------------------------------------------------- /egs/aishell/cmd.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/egs/aishell/cmd.sh -------------------------------------------------------------------------------- /egs/aishell/conf/fbank.conf: -------------------------------------------------------------------------------- 1 | --sample-frequency=16000 2 | --num-mel-bins=80 -------------------------------------------------------------------------------- /egs/aishell/figures/train-k0.2-bf15000-shuffle-ls0.1-lr.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/egs/aishell/figures/train-k0.2-bf15000-shuffle-ls0.1-lr.png -------------------------------------------------------------------------------- /egs/aishell/figures/train-k0.2-bf15000-shuffle-ls0.1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/egs/aishell/figures/train-k0.2-bf15000-shuffle-ls0.1.png -------------------------------------------------------------------------------- /egs/aishell/local/aishell_data_prep.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/egs/aishell/local/aishell_data_prep.sh -------------------------------------------------------------------------------- /egs/aishell/local/score.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/egs/aishell/local/score.sh -------------------------------------------------------------------------------- /egs/aishell/path.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/egs/aishell/path.sh -------------------------------------------------------------------------------- /egs/aishell/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/egs/aishell/run.sh -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | visdom -------------------------------------------------------------------------------- /src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/bin/recognize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/bin/recognize.py -------------------------------------------------------------------------------- /src/bin/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/bin/train.py -------------------------------------------------------------------------------- /src/data/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/data/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/data/data.py -------------------------------------------------------------------------------- /src/solver/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/solver/solver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/solver/solver.py -------------------------------------------------------------------------------- /src/transformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/transformer/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/transformer/attention.py -------------------------------------------------------------------------------- /src/transformer/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/transformer/decoder.py -------------------------------------------------------------------------------- /src/transformer/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/transformer/encoder.py -------------------------------------------------------------------------------- /src/transformer/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/transformer/loss.py -------------------------------------------------------------------------------- /src/transformer/module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/transformer/module.py -------------------------------------------------------------------------------- /src/transformer/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/transformer/optimizer.py -------------------------------------------------------------------------------- /src/transformer/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/transformer/transformer.py -------------------------------------------------------------------------------- /src/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/utils/data2json.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/utils/data2json.sh -------------------------------------------------------------------------------- /src/utils/dump.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/utils/dump.sh -------------------------------------------------------------------------------- /src/utils/filt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/utils/filt.py -------------------------------------------------------------------------------- /src/utils/json2trn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/utils/json2trn.py -------------------------------------------------------------------------------- /src/utils/mergejson.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/utils/mergejson.py -------------------------------------------------------------------------------- /src/utils/scp2json.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/utils/scp2json.py -------------------------------------------------------------------------------- /src/utils/text2token.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/utils/text2token.py -------------------------------------------------------------------------------- /src/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/src/utils/utils.py -------------------------------------------------------------------------------- /test/data/data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/test/data/data.json -------------------------------------------------------------------------------- /test/data/train_nodup_sp_units.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/test/data/train_nodup_sp_units.txt -------------------------------------------------------------------------------- /test/learn_pytorch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/test/learn_pytorch.py -------------------------------------------------------------------------------- /test/learn_visdom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/test/learn_visdom.py -------------------------------------------------------------------------------- /test/path.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/test/path.sh -------------------------------------------------------------------------------- /test/test_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/test/test_data.py -------------------------------------------------------------------------------- /test/test_decode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/test/test_decode.py -------------------------------------------------------------------------------- /tools/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/tools/Makefile -------------------------------------------------------------------------------- /tools/kaldi-io-for-python.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fchest/Speech-Transformer-multi-GPUs/HEAD/tools/kaldi-io-for-python.tar.gz --------------------------------------------------------------------------------