You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Hui Zhang
df3be4acae
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
* move s2t data preprocess into paddlespeech.dataset
* avg model, compute wer, format rsl into paddlespeech.dataset
* fix format rsl
* fix avg ckpts
|
1 year ago |
| .. |
|
fst
|
Fix some typos. (#3178)
|
1 year ago |
|
parallel
|
…
|
|
|
DER.py
|
format
|
2 years ago |
|
README.md
|
rm ds2_ol test dir
|
2 years ago |
|
__init__.py
|
more utils to support kaldi/espnet data preocess
|
3 years ago |
|
addjson.py
|
format code, test=doc
|
3 years ago |
|
apply-cmvn.py
|
format code, test=doc
|
3 years ago |
|
avg.sh
|
…
|
|
|
avg_model.py
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
|
1 year ago |
|
build_kenlm_model_from_arpa.sh
|
…
|
|
|
build_vocab.py
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
|
1 year ago |
|
caculate_rtf.py
|
lm embed and format code
|
3 years ago |
|
compute-cmvn-stats.py
|
merge deepspeech, parakeet and text_processing into paddlespeech
|
3 years ago |
|
compute-wer.py
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
|
1 year ago |
|
compute_mean_std.py
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
|
1 year ago |
|
compute_statistics.py
|
update tacotron2 voice cloning in aishell3 with new tacotron2, test=tts (#1419)
|
3 years ago |
|
copy-feats.py
|
format code, test=doc
|
3 years ago |
|
data2json.sh
|
lm embed and format code
|
3 years ago |
|
dump.sh
|
more utils to support kaldi/espnet data preocess
|
3 years ago |
|
dump_manifest.py
|
format code
|
3 years ago |
|
duration_from_maniefst.sh
|
…
|
|
|
espnet_json_to_manifest.py
|
fix utils for ngram and wfst
|
3 years ago |
|
feat-to-shape.py
|
merge deepspeech, parakeet and text_processing into paddlespeech
|
3 years ago |
|
feat_to_shape.sh
|
more utils to support kaldi/espnet data preocess
|
3 years ago |
|
filter.py
|
…
|
|
|
filter_scp.pl
|
…
|
|
|
format_data.py
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
|
1 year ago |
|
format_rsl.py
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
|
1 year ago |
|
format_triplet_data.py
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
|
1 year ago |
|
gen_duration_from_textgrid.py
|
[TTS]fix praatio version, test=tts (#1158)
|
3 years ago |
|
generate_infer_yaml.py
|
prefect the packing scripts, test=doc
|
2 years ago |
|
json2trn.py
|
format code
|
3 years ago |
|
link_wav.py
|
fix utils for ngram and wfst
|
3 years ago |
|
log.sh
|
…
|
|
|
manifest_key_value.py
|
[s2t] mv dataset into paddlespeech.dataset (#3183)
|
1 year ago |
|
md-eval.pl
|
[vector] add AMI data preparation scripts
|
3 years ago |
|
merge_scp2json.py
|
format code, test=doc
|
3 years ago |
|
ngram_train.sh
|
…
|
|
|
pack_model.sh
|
fix tiny conf
|
3 years ago |
|
parse_options.sh
|
…
|
|
|
pd_env_collect.sh
|
…
|
|
|
profile.sh
|
…
|
|
|
reduce_data_dir.sh
|
more utils to support kaldi/espnet data preocess
|
3 years ago |
|
remove_longshortdata.py
|
format code
|
3 years ago |
|
remove_longshortdata.sh
|
more utils to support kaldi/espnet data preocess
|
3 years ago |
|
run.pl
|
…
|
|
|
score_sclite.sh
|
…
|
|
|
scp2json.py
|
update format
|
3 years ago |
|
show_results.sh
|
pack model
|
3 years ago |
|
spk2utt_to_utt2spk.pl
|
…
|
|
|
split_data.sh
|
…
|
|
|
split_json.sh
|
…
|
|
|
split_scp.pl
|
…
|
|
|
spm_decode
|
…
|
|
|
spm_encode
|
…
|
|
|
spm_train
|
…
|
|
|
tarball.sh
|
…
|
|
|
text2token.py
|
lm embed and format code
|
3 years ago |
|
text_to_lexicon.py
|
mv text_to_lexicon.py to utils
|
2 years ago |
|
tokenizer.perl
|
Fix some typos. (#3178)
|
1 year ago |
|
train_arpa_with_kenlm.sh
|
…
|
|
|
update_json.sh
|
add utils
|
3 years ago |
|
utility.sh
|
…
|
|
|
utt2spk_to_spk2utt.pl
|
…
|
|
|
zh_tn.py
|
format
|
2 years ago |
