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

Soem bug fixes

This commit is contained in:
Eren Golge 2019-01-17 15:48:22 +01:00
parent 4431e04b48
commit 562d73d3d1
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
config.json
View File

@ -10,9 +10,9 @@
"sample_rate": 16000, // wav sample-rate. If different than the original data, it is resampled. "sample_rate": 16000, // wav sample-rate. If different than the original data, it is resampled.
"frame_length_ms": 50, // stft window length in ms. "frame_length_ms": 50, // stft window length in ms.
"frame_shift_ms": 12.5, // stft window hop-lengh in ms. "frame_shift_ms": 12.5, // stft window hop-lengh in ms.
"preemphasis": 0.97, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. "preemphasis": 0.98, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
"min_level_db": -100, // normalization range "min_level_db": -100, // normalization range
"ref_level_db": 20, // reference level db, theoretically 20db is the sound of air. "ref_level_db": 40, // reference level db, theoretically 20db is the sound of air.
"power": 1.5, // value to sharpen wav signals after GL algorithm. "power": 1.5, // value to sharpen wav signals after GL algorithm.
"griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation. "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
// Normalization parameters // Normalization parameters
@ -52,7 +52,7 @@
"output_path": "/media/erogol/data_ssd/Data/models/en_UK/", // DATASET-RELATED: output path for all training outputs. "output_path": "/media/erogol/data_ssd/Data/models/en_UK/", // DATASET-RELATED: output path for all training outputs.
"num_loader_workers": 8, // number of training data loader processes. Don't set it too big. 4-8 are good values. "num_loader_workers": 8, // number of training data loader processes. Don't set it too big. 4-8 are good values.
"num_val_loader_workers": 4, // number of evaluation data loader processes. "num_val_loader_workers": 4, // number of evaluation data loader processes.
"phoneme_cache_path": "tmp_en_uk", // phoneme computation is slow, therefore, it caches results in the given folder. "phoneme_cache_path": "tmp_phonemes_gb", // phoneme computation is slow, therefore, it caches results in the given folder.
"use_phonemes": true, // use phonemes instead of raw characters. It is suggested for better pronounciation. "use_phonemes": true, // use phonemes instead of raw characters. It is suggested for better pronounciation.
"phoneme_language": "en-us" // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages "phoneme_language": "en-gb" // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages
} }

2
layers/tacotron.py
View File

@ -413,7 +413,7 @@ class Decoder(nn.Module):
for idx in range(len(self.decoder_rnns)): for idx in range(len(self.decoder_rnns)):
decoder_rnn_hiddens[idx] = self.decoder_rnns[idx]( decoder_rnn_hiddens[idx] = self.decoder_rnns[idx](
decoder_input, decoder_rnn_hiddens[idx]) decoder_input, decoder_rnn_hiddens[idx])
# Residual connectinon # Residual connection
decoder_input = decoder_rnn_hiddens[idx] + decoder_input decoder_input = decoder_rnn_hiddens[idx] + decoder_input
decoder_output = decoder_input decoder_output = decoder_input
del decoder_input del decoder_input