Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
language-and-voice-lab
/
talromur_f_loudnorm_xvector_finetune_fastspeech2
like
0
Text-to-Speech
ESPnet
talromur
English
audio
arxiv:
1804.00015
License:
cc-by-4.0
Model card
Files
Files and versions
Community
Deploy
Use this model
main
talromur_f_loudnorm_xvector_finetune_fastspeech2
/
exp
/
tts_finetune_f_loudnorm_xvector_fastspeech2
/
images
1 contributor
History:
1 commit
GunnarThor
Update model
d081f5e
3 months ago
backward_time.png
41.4 kB
Update model
3 months ago
clip.png
18.3 kB
Update model
3 months ago
decoder_alpha.png
40.9 kB
Update model
3 months ago
duration_loss.png
37.6 kB
Update model
3 months ago
encoder_alpha.png
46.2 kB
Update model
3 months ago
energy_loss.png
38.2 kB
Update model
3 months ago
forward_time.png
46.2 kB
Update model
3 months ago
gpu_max_cached_mem_GB.png
26.8 kB
Update model
3 months ago
grad_norm.png
25.8 kB
Update model
3 months ago
iter_time.png
24.5 kB
Update model
3 months ago
l1_loss.png
32.6 kB
Update model
3 months ago
loss.png
31.8 kB
Update model
3 months ago
loss_scale.png
17.8 kB
Update model
3 months ago
optim0_lr0.png
27.7 kB
Update model
3 months ago
optim_step_time.png
58.7 kB
Update model
3 months ago
pitch_loss.png
36.3 kB
Update model
3 months ago
train_time.png
35.2 kB
Update model
3 months ago