mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
ac84220de9
* Copy files for editing. * Use librispeech + gigaspeech with modified conformer. * Support specifying number of workers for on-the-fly feature extraction. * Feature extraction code for GigaSpeech. * Combine XL splits lazily during training. * Fix warnings in decoding. * Add decoding code for GigaSpeech. * Fix decoding the gigaspeech dataset. We have to use the decoder/joiner networks for the GigaSpeech dataset. * Disable speed perturbe for XL subset. * Compute the Nbest oracle WER for RNN-T decoding. * Minor fixes. * Minor fixes. * Add results. * Update results. * Update CI. * Update results. * Fix style issues. * Update results. * Fix style issues.
52 lines
1.4 KiB
Bash
Executable File
52 lines
1.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
log() {
|
|
# This function is from espnet
|
|
local fname=${BASH_SOURCE[1]##*/}
|
|
echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
|
|
}
|
|
|
|
cd egs/librispeech/ASR
|
|
|
|
repo_url=https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless3-2022-04-29
|
|
|
|
log "Downloading pre-trained model from $repo_url"
|
|
git lfs install
|
|
git clone $repo_url
|
|
repo=$(basename $repo_url)
|
|
|
|
log "Display test files"
|
|
tree $repo/
|
|
soxi $repo/test_wavs/*.wav
|
|
ls -lh $repo/test_wavs/*.wav
|
|
|
|
pushd $repo/exp
|
|
ln -s pretrained-epoch-25-avg-6.pt pretrained.pt
|
|
popd
|
|
|
|
for sym in 1 2 3; do
|
|
log "Greedy search with --max-sym-per-frame $sym"
|
|
|
|
./pruned_transducer_stateless3/pretrained.py \
|
|
--method greedy_search \
|
|
--max-sym-per-frame $sym \
|
|
--checkpoint $repo/exp/pretrained.pt \
|
|
--bpe-model $repo/data/lang_bpe_500/bpe.model \
|
|
$repo/test_wavs/1089-134686-0001.wav \
|
|
$repo/test_wavs/1221-135766-0001.wav \
|
|
$repo/test_wavs/1221-135766-0002.wav
|
|
done
|
|
|
|
for method in modified_beam_search beam_search fast_beam_search; do
|
|
log "$method"
|
|
|
|
./pruned_transducer_stateless3/pretrained.py \
|
|
--method $method \
|
|
--beam-size 4 \
|
|
--checkpoint $repo/exp/pretrained.pt \
|
|
--bpe-model $repo/data/lang_bpe_500/bpe.model \
|
|
$repo/test_wavs/1089-134686-0001.wav \
|
|
$repo/test_wavs/1221-135766-0001.wav \
|
|
$repo/test_wavs/1221-135766-0002.wav
|
|
done
|