issues
search
lucidrains
/
audiolm-pytorch
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.32k
stars
249
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
hi. If i want to train text to Chinese speech audiolm , what confuse me is that pretrained hubert model is English-style, Does it affect my Chinese version training? Or i have to re-train hubert with my own large chinese dataset ? Appreciate !!!! @lucidrains
#219
hyhzl
closed
11 months ago
4
Is resampling needed when using EnCodec?
#218
m-pana
opened
11 months ago
7
yolov5
#216
fangwei888
opened
11 months ago
1
AssertionError: only one Trainer can be instantiated at a time for training
#215
tiansiyuan
opened
11 months ago
1
Separate transformer and trainer checkpoint load logic
#214
LWprogramming
closed
11 months ago
1
How to run the inference?
#213
LianaN
closed
11 months ago
6
TypeError: cannot unpack non-iterable NoneType object
#212
tiansiyuan
closed
11 months ago
16
When running the example code, I get an error where the trainer says to be instantiated twice:
#211
LukasNel
closed
11 months ago
6
accelerate's wait_for_everyone hangs on the final step of training coarse/fine transformer
#210
LWprogramming
closed
11 months ago
4
Accelerate failing on multi-gpu rng synchronization
#209
LWprogramming
closed
11 months ago
15
Question about length of data in training \ generating
#208
amitaie
closed
9 months ago
0
Implement accelerate support for semantic/coarse/fine transformers
#207
LWprogramming
closed
11 months ago
2
Change torch.no_grad() to torch.inference_mode()
#206
LWprogramming
closed
1 year ago
1
Max length fix
#205
LWprogramming
closed
1 year ago
1
Questions about training Soundstream: poor intelligibility and gradients explosion after 10k steps. (sr=16k, B=96)
#204
Makiyuyuko
opened
1 year ago
1
OpenBLAS/OpenMP Loop error message
#203
LWprogramming
closed
1 year ago
8
generation form of the inference
#201
Hit1ron
closed
1 year ago
4
Eos handling
#200
LWprogramming
closed
1 year ago
3
Audio generation failing at FineTransformer
#199
LWprogramming
closed
1 year ago
15
pin sklearn exactly to 0.24.0
#198
LWprogramming
closed
1 year ago
7
'SemanticTransformerWrapper' object has no attribute 'embed_text'
#197
jinyuli
closed
1 year ago
4
A problem with EncodecWrapper()
#196
Leezp99
closed
1 year ago
3
Bug fix in encodec.py
#195
yang1fan2
closed
1 year ago
1
`MultiScaleDiscriminator` differs from paper
#194
haydenshively
closed
1 year ago
3
Improve ComplexConv2d FSDP compatibility
#193
haydenshively
closed
1 year ago
3
Question about the generate
#192
asr-pub
opened
1 year ago
0
Poor audio quality
#191
cpdu
closed
1 year ago
1
a small question about the loss function
#190
PB20000090
closed
1 year ago
1
Fix off-by-one error in train step update
#189
LWprogramming
closed
1 year ago
1
Fix path type
#188
LWprogramming
closed
1 year ago
0
Load from correct self.steps to resume training
#187
LWprogramming
closed
1 year ago
1
question about the semantic process
#186
asr-pub
closed
1 year ago
3
Loss about CoarseTransformerWrapper
#185
asr-pub
closed
1 year ago
2
Something wrong when i use the “soundstream” repo
#184
wangyuxuan11
opened
1 year ago
1
training data
#183
linlongrd
opened
1 year ago
0
can not install audiolm-pytorch
#182
linlongrd
closed
1 year ago
4
/path/to/audio/files
#181
linlongrd
opened
1 year ago
0
more demo needed
#179
fire-keeper
opened
1 year ago
0
Use a pretrained model as a discriminator (and for feature maps)
#177
turian
closed
1 year ago
5
BIG NEWS!!!!!! Encodec License change MIT License!!!
#176
fd873630
closed
1 year ago
0
update readme encodec mit license
#175
LWprogramming
closed
1 year ago
1
ComplexSTFTDiscriminator diverges from paper
#174
eagomez2
closed
1 year ago
5
Potentially useful pretrained models
#169
gkucsko
closed
1 year ago
2
Confusion about the coarse transformer trainer
#167
xtluo
closed
1 year ago
1
padding issue for CausalConv1d
#166
YoungloLee
closed
1 year ago
6
Training curves for discriminator losses?
#165
turian
closed
1 year ago
1
Bug? mask = True
#164
maitycyrus
closed
1 year ago
1
i get the noise!
#163
iamliulong
opened
1 year ago
1
Update encodec.py
#162
syjunghwang
closed
1 year ago
0
Saves corrupt audio
#161
sulkytejas
opened
1 year ago
2
Previous
Next