Commit 26c82682 authored by Phil Wang's avatar Phil Wang
Browse files

ok it is working

parent 2de8bb00

README.md

+2 −1
Original line number Diff line number Diff line
@@ -95,7 +95,8 @@ wav2vec = HubertWithKmeans( 
semantic_transformer = SemanticTransformer(

    num_semantic_tokens = wav2vec.codebook_size,

    dim = 1024,

    depth = 6

    depth = 6,

    audio_text_condition = True      # this must be set to True (same for CoarseTransformer and FineTransformers)

).cuda()



trainer = SemanticTransformerTrainer(

setup.py

+2 −2
Original line number Diff line number Diff line
@@ -3,7 +3,7 @@ from setuptools import setup, find_packages 
setup(

  name = 'musiclm-pytorch',

  packages = find_packages(exclude=[]),

  version = '0.0.7',

  version = '0.0.8',

  license='MIT',

  description = 'MusicLM - AudioLM + Audio CLIP to text to music synthesis',

  author = 'Phil Wang',
@@ -19,7 +19,7 @@ setup( 
    'contrastive learning'

  ],

  install_requires=[

    'audiolm-pytorch>=0.9.2',

    'audiolm-pytorch>=0.9.3',

    'beartype',

    'einops>=0.4',

    'vector-quantize-pytorch>=1.0.0',