issues
search
lucidrains
/
audiolm-pytorch
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.45k
stars
266
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
CUDA error: an illegal memory access was encountered
#281
bulieme
opened
8 hours ago
0
Does SoundStream support streaming inference? If so, can you provide the relevant code?
#280
dengcunqin
opened
3 days ago
0
SoundStream training hangs using accelerate launch and the use_finite_scalar_quantizer=True setting
#279
ThomasLWang
closed
1 week ago
23
How to use multiple GPUs for training and inference?
#278
Oyiyi
opened
3 months ago
0
what's your loss rate?
#277
Oyiyi
opened
3 months ago
0
Trying to overfit SounsStream
#276
hishammadcor
opened
3 months ago
0
Why is Encodec only encoding 1 frame?
#275
sivannavis
closed
5 months ago
1
checkpoint
#274
why414
opened
7 months ago
0
Classifier for detecting synthetic speech
#273
Ashigarg123
opened
8 months ago
0
Model cascade training
#272
a897456
opened
8 months ago
0
Audiolm as an embedder model?
#271
Darel13712
opened
9 months ago
0
Soundstream training using birdsongs. Any guidance appreciated!
#270
haydensflee
opened
9 months ago
0
About get_embeds function
#269
jihoojung0106
opened
9 months ago
1
Why not use the output of Attention in Transformer?
#268
jihoojung0106
closed
9 months ago
0
AssertionError: File Not Found: data/hyp.scratch.yaml
#267
zrshello
closed
9 months ago
1
skip the eos when adding offset to avoid overlapping
#266
biendltb
closed
10 months ago
5
fix wrong tensor assignment of the output of attention
#265
biendltb
closed
10 months ago
1
Training dataset
#264
hahust191806
opened
10 months ago
0
Missing softmax after Linear layer
#263
biendltb
closed
9 months ago
1
Cannot retrieve dependency version for gateloop-transformer>=0.5.2, possible regression?
#262
afreemanio
closed
10 months ago
1
Removal of the last token id from fine_token_ids in FineTransformerWrapper.forward()
#261
biendltb
closed
10 months ago
1
Fix #259
#260
orrp
closed
11 months ago
1
`data_max_length_seconds` causes typecheck error in `CoarseTransformerTrainer`
#259
orrp
closed
11 months ago
0
`use_wandb_tracking` was not stored in most Trainers when it is `False`
#258
orrp
closed
11 months ago
1
Added wandb tracking to SemanticTransformerTrainer, CoarseTransformerTrainer, and FineTransformerTrainer
#257
LukasNel
closed
11 months ago
1
Soundstream discriminator clip_grad_norm - some params are not clipped.
#256
avihu111
closed
11 months ago
3
Gradient Issue when Finetuning
#255
tysonjordan
closed
10 months ago
0
Error in exporting soundstream to onnx
#254
kalradivyanshu
opened
1 year ago
14
Only noise as a result
#253
mpastewski
opened
1 year ago
4
Update RVQ projection layers during training
#251
ilya16
closed
1 year ago
1
Question: Random semantic embedding in SemanticTransformer?
#249
stg1205
opened
1 year ago
1
bugfix - swap codec variable for course wrapper
#248
rgxb2807
closed
1 year ago
1
I very thanks for your work. But when i train the soundstream model, why does it need a pre-trained Encodec and then error?
#247
DingWeiPeng
closed
1 year ago
0
IndexError Using Encodec and setting return_coarse_generated_wave=True
#246
rgxb2807
closed
1 year ago
5
Fixed typo in README.md
#244
y4umeng
closed
1 year ago
0
Bugfix - Fixing validation dataset variable on FineTransformerTrainer
#243
rgxb2807
closed
1 year ago
1
Question: Any way to specify validation dataset for SemanticTransformer, CoarseTransformer and FineTransformer?
#242
rgxb2807
closed
1 year ago
2
Question: Checkpoint of the model
#241
fernandals
opened
1 year ago
1
Question: Are there any work arounds for using DeepSpeed for multi-gpu training
#240
rgxb2807
opened
1 year ago
4
Question: How to load pythorch format as HubertWithKmeans?
#239
Selectorrr
opened
1 year ago
0
Question on discrepancy between original data and reconstructed data sizes
#238
tysonjordan
opened
1 year ago
1
Bug in generation when generating with Encodec
#236
FrancescoVV
closed
1 year ago
7
have trouble to generate semantic tokens using the demo code
#235
dwangF0
closed
1 year ago
2
multi-gpu training not working with accelerate
#234
FrancescoVV
closed
1 year ago
13
Does VALL-E follow the same semantic/coarse hierarchical structure as AudioLM?
#233
williamluer
closed
1 year ago
3
Likely beartype package breakage
#231
rsxdalv
closed
1 year ago
1
Question about 'attention bias not supported for flash attention'
#230
amitaie
opened
1 year ago
2
Error when running 3rd cell in demo ipynb
#229
uday18git
closed
1 year ago
0
Code Refactoring
#228
tosemml
closed
1 year ago
1
pretrained soundstream weights?
#227
muazhuda
opened
1 year ago
1
Next