Hugging Face's logo

dkounadis
/
artificial-styletts2

Text-to-Audio
Audiocraft
English
audiogen
styletts2
shift-tts
sound
audio-generation
text-to-speech
mimic3
Model card Files Community
4
artificial-styletts2 / audiocraft /lm.py

Commit History

soudscape discard last 1s from AudioGen - avoids splash sound
a84b206

Dionyssos commited on

debug long sounds
3ac9f34

Dionyssos commited on

apply null cond lm.forw()
6cb7713

Dionyssos commited on

revert pattern preserves 4
dcfe0d4

Dionyssos commited on

AudioGen class
54adc39

Dionyssos commited on

distortion on barging DEBUG
e70ad00

Dionyssos commited on

instantiate audiogen in demo
d912185

Dionyssos commited on

fx k,v history after project
60fbcf9

Dionyssos commited on

kv history @ each transf layer
731cb10

Dionyssos commited on

DEBUG steaming past key changes 47x during next token calc
e83a997

Dionyssos commited on

DEBUG: cross_attention_src = query or key?
a0ce150

Dionyssos commited on

revert transformer.py
2e6c69d

Dionyssos commited on

LM has virtual 2nd batch
3eec6d2

Dionyssos commited on

duplicate xN_DRAW - for long gen
d9889a1

Dionyssos commited on

index out of bounds 2048 @ dequantize()
27d24be

Dionyssos commited on

prompt_token defaults to torch.zeros()
8639464

Dionyssos commited on

cleanup Vq
fe62fb4

Dionyssos commited on

clean unused functions
e366cd5

Dionyssos commited on

debug special token
0a8807e

Dionyssos commited on

del xtr funs
531e776

Dionyssos commited on

audiocraft
d72b2c3

Dionyssos commited on