mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 01:52:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Small fix

Browse Source
This commit is contained in:
Yifan Yang 2024-12-31 00:27:08 +08:00 committed by GitHub
parent 48088cb807
commit dc55d6e076
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
egs/wenetspeech4tts/TTS/prepare.sh
View File

@ -10,9 +10,9 @@ stop_stage=4
dl_dir=$PWD/download dl_dir=$PWD/download
dataset_parts="Premium" # Basic for all 10k hours data, Premium for about 10% of the data dataset_parts="Premium" # Basic for all 7226 hours data, Premium for 945 hours subset.
text_extractor="pypinyin_initials_finals" # default is espeak for English text_extractor="pypinyin_initials_finals" # default is espeak for English
audio_extractor="Encodec" # or Fbank audio_extractor="Encodec" # or Fbank
audio_feats_dir=data/tokenized audio_feats_dir=data/tokenized
@ -63,7 +63,7 @@ if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
--audio-extractor ${audio_extractor} \ --audio-extractor ${audio_extractor} \
--batch-duration 2500 --prefix "wenetspeech4tts" \ --batch-duration 2500 --prefix "wenetspeech4tts" \
--src-dir "data/manifests" \ --src-dir "data/manifests" \
--split 100 \ --split 100 \
--output-dir "${audio_feats_dir}/wenetspeech4tts_${dataset_parts}_split_100" --output-dir "${audio_feats_dir}/wenetspeech4tts_${dataset_parts}_split_100"
cp ${audio_feats_dir}/wenetspeech4tts_${dataset_parts}_split_100/unique_text_tokens.k2symbols ${audio_feats_dir} cp ${audio_feats_dir}/wenetspeech4tts_${dataset_parts}_split_100/unique_text_tokens.k2symbols ${audio_feats_dir}
fi fi