Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

config update for nancy

This commit is contained in:
Eren Golge 2019-03-12 17:02:56 +01:00
parent bbd90c3b4d
commit 645f4fc886
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.compute
View File

@ -3,5 +3,5 @@ ls ${SHARED_DIR}/data/
pip3 install https://download.pytorch.org/whl/cu100/torch-1.0.1.post2-cp36-cp36m-linux_x86_64.whl
yes | apt-get install espeak
python3 setup.py develop
# python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ --restore_path ${USER_DIR}/best_model.pth.tar
python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/
python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/ --restore_path ${USER_DIR}/best_model.pth.tar
# python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/

4
config_cluster.json
View File

@ -6,7 +6,7 @@
// Audio processing parameters
"num_mels": 80, // size of the mel spec frame.
"num_freq": 1025, // number of stft frequency levels. Size of the linear spectogram frame.
"sample_rate": 22050, // wav sample-rate. If different than the original data, it is resampled.
"sample_rate": 16000, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
"frame_length_ms": 50, // stft window length in ms.
"frame_shift_ms": 12.5, // stft window hop-lengh in ms.
"preemphasis": 0.98, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
@ -21,7 +21,7 @@
"clip_norm": true, // clip normalized values into the range.
"mel_fmin": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
"mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!!
"do_trim_silence": false // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
"do_trim_silence": true // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
},
"distributed":{