|
|
|
#!/bin/bash
|
E2E/Streaming Transformer/Conformer ASR (#578)
* add cmvn and label smoothing loss layer
* add layer for transformer
* add glu and conformer conv
* add torch compatiable hack, mask funcs
* not hack size since it exists
* add test; attention
* add attention, common utils, hack paddle
* add audio utils
* conformer batch padding mask bug fix #223
* fix typo, python infer fix rnn mem opt name error and batchnorm1d, will be available at 2.0.2
* fix ci
* fix ci
* add encoder
* refactor egs
* add decoder
* refactor ctc, add ctc align, refactor ckpt, add warmup lr scheduler, cmvn utils
* refactor docs
* add fix
* fix readme
* fix bugs, refactor collator, add pad_sequence, fix ckpt bugs
* fix docstring
* refactor data feed order
* add u2 model
* refactor cmvn, test
* add utils
* add u2 config
* fix bugs
* fix bugs
* fix autograd maybe has problem when using inplace operation
* refactor data, build vocab; add format data
* fix text featurizer
* refactor build vocab
* add fbank, refactor feature of speech
* refactor audio feat
* refactor data preprare
* refactor data
* model init from config
* add u2 bins
* flake8
* can train
* fix bugs, add coverage, add scripts
* test can run
* fix data
* speed perturb with sox
* add spec aug
* fix for train
* fix train logitc
* fix logger
* log valid loss, time dataset process
* using np for speed perturb, remove some debug log of grad clip
* fix logger
* fix build vocab
* fix logger name
* using module logger as default
* fix
* fix install
* reorder imports
* fix board logger
* fix logger
* kaldi fbank and mfcc
* fix cmvn and print prarams
* fix add_eos_sos and cmvn
* fix cmvn compute
* fix logger and cmvn
* fix subsampling, label smoothing loss, remove useless
* add notebook test
* fix log
* fix tb logger
* multi gpu valid
* fix log
* fix log
* fix config
* fix compute cmvn, need paddle 2.1
* add cmvn notebook
* fix layer tools
* fix compute cmvn
* add rtf
* fix decoding
* fix layer tools
* fix log, add avg script
* more avg and test info
* fix dataset pickle problem; using 2.1 paddle; num_workers can > 0; ckpt save in exp dir;fix setup.sh;
* add vimrc
* refactor tiny script, add transformer and stream conf
* spm demo; librisppech scripts and confs
* fix log
* add librispeech scripts
* refactor data pipe; fix conf; fix u2 default params
* fix bugs
* refactor aishell scripts
* fix test
* fix cmvn
* fix s0 scripts
* fix ds2 scripts and bugs
* fix dev & test dataset filter
* fix dataset filter
* filter dev
* fix ckpt path
* filter test, since librispeech will cause OOM, but all test wer will be worse, since mismatch train with test
* add comment
* add syllable doc
* fix ds2 configs
* add doc
* add pypinyin tools
* fix decoder using blank_id=0
* mmseg with pybind11
* format code
4 years ago
|
|
|
|
|
|
|
stage=-1
|
|
|
|
stop_stage=100
|
|
|
|
|
|
|
|
# bpemode (unigram or bpe)
|
|
|
|
nbpe=200
|
|
|
|
bpemode=unigram
|
|
|
|
bpeprefix="data/bpe_${bpemode}_${nbpe}"
|
|
|
|
|
|
|
|
source ${MAIN_ROOT}/utils/parse_options.sh
|
|
|
|
|
|
|
|
mkdir -p data
|
|
|
|
TARGET_DIR=${MAIN_ROOT}/examples/dataset
|
|
|
|
mkdir -p ${TARGET_DIR}
|
|
|
|
|
|
|
|
if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
|
|
|
|
# download data, generate manifests
|
|
|
|
python3 ${TARGET_DIR}/librispeech/librispeech.py \
|
|
|
|
--manifest_prefix="data/manifest" \
|
|
|
|
--target_dir="${TARGET_DIR}/librispeech" \
|
|
|
|
--full_download="False"
|
|
|
|
|
|
|
|
if [ $? -ne 0 ]; then
|
|
|
|
echo "Prepare LibriSpeech failed. Terminated."
|
|
|
|
exit 1
|
|
|
|
fi
|
|
|
|
|
|
|
|
head -n 64 data/manifest.dev-clean > data/manifest.tiny.raw
|
|
|
|
fi
|
|
|
|
|
|
|
|
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
|
|
|
|
# build vocabulary
|
|
|
|
python3 ${MAIN_ROOT}/utils/build_vocab.py \
|
|
|
|
--unit_type "spm" \
|
|
|
|
--spm_vocab_size=${nbpe} \
|
|
|
|
--spm_mode ${bpemode} \
|
|
|
|
--spm_model_prefix ${bpeprefix} \
|
|
|
|
--vocab_path="data/vocab.txt" \
|
|
|
|
--manifest_paths="data/manifest.tiny.raw"
|
|
|
|
|
|
|
|
if [ $? -ne 0 ]; then
|
|
|
|
echo "Build vocabulary failed. Terminated."
|
|
|
|
exit 1
|
|
|
|
fi
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
|
|
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
|
|
|
|
# compute mean and stddev for normalizer
|
|
|
|
python3 ${MAIN_ROOT}/utils/compute_mean_std.py \
|
|
|
|
--manifest_path="data/manifest.tiny.raw" \
|
|
|
|
--num_samples=64 \
|
|
|
|
--specgram_type="fbank" \
|
|
|
|
--feat_dim=80 \
|
|
|
|
--delta_delta=false \
|
|
|
|
--sample_rate=16000 \
|
|
|
|
--stride_ms=10.0 \
|
|
|
|
--window_ms=25.0 \
|
|
|
|
--use_dB_normalization=False \
|
|
|
|
--num_workers=2 \
|
|
|
|
--output_path="data/mean_std.json"
|
|
|
|
|
|
|
|
if [ $? -ne 0 ]; then
|
|
|
|
echo "Compute mean and stddev failed. Terminated."
|
|
|
|
exit 1
|
|
|
|
fi
|
|
|
|
fi
|
|
|
|
|
|
|
|
|
|
|
|
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
|
|
|
|
# format manifest with tokenids, vocab size
|
|
|
|
python3 ${MAIN_ROOT}/utils/format_data.py \
|
|
|
|
--feat_type "raw" \
|
|
|
|
--cmvn_path "data/mean_std.json" \
|
|
|
|
--unit_type "spm" \
|
|
|
|
--spm_model_prefix ${bpeprefix} \
|
|
|
|
--vocab_path="data/vocab.txt" \
|
|
|
|
--manifest_path="data/manifest.tiny.raw" \
|
|
|
|
--output_path="data/manifest.tiny"
|
|
|
|
|
|
|
|
|
|
|
|
if [ $? -ne 0 ]; then
|
|
|
|
echo "Formt mnaifest failed. Terminated."
|
|
|
|
exit 1
|
|
|
|
fi
|
|
|
|
fi
|
|
|
|
|
|
|
|
echo "LibriSpeech Data preparation done."
|
|
|
|
exit 0
|