mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
96 lines
3.0 KiB
Bash
96 lines
3.0 KiB
Bash
#!/usr/bin/env bash
|
|
|
|
# Prepare script for MLS English ASR recipe in icefall
|
|
# This recipe uses on-the-fly feature extraction, so it skips manifest
|
|
# and feature generation steps used in other recipes.
|
|
|
|
# fix segmentation fault reported in https://github.com/k2-fsa/icefall/issues/674
|
|
export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
|
|
|
|
set -eou pipefail
|
|
|
|
nj=15
|
|
stage=-1
|
|
stop_stage=100
|
|
|
|
# Configuration for BPE tokenizer
|
|
vocab_sizes=(2000) # You can add more sizes like (500 1000 2000) for comparison
|
|
|
|
# Directory where dataset will be downloaded
|
|
dl_dir=$PWD/download
|
|
|
|
. shared/parse_options.sh || exit 1
|
|
|
|
# All files generated by this script are saved in "data".
|
|
mkdir -p data
|
|
|
|
log() {
|
|
local fname=${BASH_SOURCE[1]##*/}
|
|
echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
|
|
}
|
|
|
|
log "Starting MLS English data preparation"
|
|
|
|
if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
|
|
log "Stage 0: Download MLS English dataset"
|
|
if [ ! -d $dl_dir/mls_english ]; then
|
|
if ! git clone https://huggingface.co/datasets/parler-tts/mls_eng $dl_dir/mls_english; then
|
|
log "Failed to download MLS English dataset"
|
|
exit 1
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 1 ] && [ $stop_stage -ge 1 ]; then
|
|
log "Stage 1: Prepare MLS English manifests and compute fbank"
|
|
# We assume that you have downloaded the MLS English corpus
|
|
# to $dl_dir/mls_english
|
|
mkdir -p data/manifests
|
|
if [ ! -e data/mls_english.done ]; then
|
|
# lhotse prepare mls_english -j $nj $dl_dir/mls_english data/manifests
|
|
python local/compute_fbank_mls_english.py --manifest-dir data/manifests --audio-dir data/audio --dl-dir $dl_dir/mls_english
|
|
touch data/manifests/.mls_english.done
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
|
|
log "Stage 2: Validate MLS English manifests"
|
|
if [ ! -e data/manifests/.mls_english-validated.done ]; then
|
|
python local/validate_manifest.py --manifest data/manifests/mls_english_cuts_train.jsonl.gz
|
|
python local/validate_manifest.py --manifest data/manifests/mls_english_cuts_dev.jsonl.gz
|
|
python local/validate_manifest.py --manifest data/manifests/mls_english_cuts_test.jsonl.gz
|
|
touch data/manifests/.mls_english-validated.done
|
|
fi
|
|
fi
|
|
|
|
|
|
mkdir -p data/lang
|
|
lang_dir=data/lang
|
|
|
|
if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then
|
|
log "Stage 3: Prepare transcript for BPE training"
|
|
if [ ! -f $lang_dir/transcript.txt ]; then
|
|
log "Generating transcripts for BPE training"
|
|
./local/utils/generate_transcript.py --lang-dir $lang_dir
|
|
fi
|
|
fi
|
|
|
|
if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then
|
|
log "Stage 4: Prepare BPE tokenizer"
|
|
|
|
for vocab_size in ${vocab_sizes[@]}; do
|
|
log "Training BPE model with vocab_size=${vocab_size}"
|
|
bpe_dir=data/lang/bpe_${vocab_size}
|
|
mkdir -p $bpe_dir
|
|
|
|
if [ ! -f $bpe_dir/bpe.model ]; then
|
|
./local/train_bpe_model.py \
|
|
--lang-dir $bpe_dir \
|
|
--vocab-size $vocab_size \
|
|
--transcript $lang_dir/transcript.txt
|
|
fi
|
|
done
|
|
fi
|
|
|
|
log "MLS English data preparation completed successfully"
|