Commit 25c5ce6c authored by Phil Wang's avatar Phil Wang
Browse files

only log errors

parent ab58e6ee

README.md

+1 −1
Original line number Diff line number Diff line
@@ -201,11 +201,11 @@ generated_wav_with_text_condition = audiolm(text = ['chirping of birds and the d 
- [x] refactor so semantic transformer has a wrapper to that handles unique consecutives as well as wav to hubert or vq-wav2vec

- [x] simply not self attend to eos token on the prompting side (semantic for coarse transformer, coarse for fine transformer)

- [x] add structured dropout from forgetful causal masking, far better than traditional dropouts

- [x] figure out how to suppress logging in fairseq



- [ ] figure out how to do the normalization across each dimension mentioned in the paper, but ignore it for v1 of the framework

- [ ] offer option to weight tie coarse, fine, and semantic embeddings across the 3 hierarchical transformers

- [ ] DRY a little at the end

- [ ] figure out how to suppress logging in fairseq

- [ ] test with speech synthesis for starters

- [ ] abstract out conditioning + classifier free guidance into external module or potentially a package

- [ ] add option to use flash attention

audiolm_pytorch/hubert_kmeans.py

+4 −0
Original line number Diff line number Diff line
@@ -5,12 +5,16 @@ from torch import nn 
from einops import rearrange, pack, unpack



import joblib



import fairseq



from torchaudio.functional import resample



from audiolm_pytorch.utils import curtail_to_multiple



import logging

logging.root.setLevel(logging.ERROR)



def exists(val):

    return val is not None

audiolm_pytorch/vq_wav2vec.py

+3 −0
Original line number Diff line number Diff line
@@ -10,6 +10,9 @@ from torchaudio.functional import resample 


from audiolm_pytorch.utils import curtail_to_multiple



import logging

logging.root.setLevel(logging.ERROR)



def exists(val):

    return val is not None

setup.py

+1 −1
Original line number Diff line number Diff line
@@ -3,7 +3,7 @@ from setuptools import setup, find_packages 
setup(

  name = 'audiolm-pytorch',

  packages = find_packages(exclude=[]),

  version = '0.1.5',

  version = '0.1.6',

  license='MIT',

  description = 'AudioLM - Language Modeling Approach to Audio Generation from Google Research - Pytorch',

  author = 'Phil Wang',