issues
search
yl4579
/
AuxiliaryASR
Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)
MIT License
108
stars
30
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to train ZH-EN duo language aligner?
#12
Stardust-minus
opened
4 months ago
1
Error Message: RuntimeError: Argument #4: Padding size should be less than the corresponding input dimension, but got: padding (1024, 1024) at dimension 2 of input [1, 65621, 2]
#11
GUUser91
opened
8 months ago
3
Why is " " used as the blank in the CTCLoss?
#10
jamesparsloe
opened
1 year ago
0
Multiple GPU training and changing to librosa mel spec?
#9
crypticsymmetry
closed
1 year ago
2
Is there anyone who has used the phonemizer? Any advice, please, on how to change the code correctly
#8
ahmeftah
closed
1 year ago
3
get error
#7
MMMMichaelzhang
closed
2 years ago
28
why mel_spectrogam feature extracting using only MEL_PARAMS here?
#6
superhg
closed
2 years ago
3
Update text_utils.py
#5
woters
closed
2 years ago
0
About the loss
#4
Charlottecuc
closed
2 years ago
4
how to make word_index_dict.txt
#3
Ruinmou
closed
2 years ago
3
how to train for mandarin asr?
#2
MMMMichaelzhang
closed
2 years ago
8
How much data did you use to train the model?
#1
Charlottecuc
closed
2 years ago
1