it is done

conds = quantizer(wavs = wavs, namespace = 'semantic') # (2, 8, 1024) - 8 is number of quantizers

```

After much training, you will pass your finetuned or trained-from-scratch `AudioLM` and `MuLaN` wrapped in `MuLaNEmbedQuantizer` to the `MusicLM`

To train (or finetune) the three transformers that are a part of `AudioLM`, you simply follow the instructions over at `audiolm-pytorch` for training, but pass in the `MulanEmbedQuantizer` instance to the training classes under the keyword `audio_conditioner`

ex. `SemanticTransformerTrainer`

```python

import torch

from audiolm_pytorch import HubertWithKmeans, SemanticTransformer, SemanticTransformerTrainer

wav2vec = HubertWithKmeans(

    checkpoint_path = './hubert/hubert_base_ls960.pt',

    kmeans_path = './hubert/hubert_base_ls960_L9_km500.bin'

)

semantic_transformer = SemanticTransformer(

    num_semantic_tokens = wav2vec.codebook_size,

    dim = 1024,

    depth = 6

).cuda()

trainer = SemanticTransformerTrainer(

    transformer = semantic_transformer,

    wav2vec = wav2vec,

    audio_conditioner = quantizer,   # pass in the MulanEmbedQuantizer instance above

    folder ='/path/to/audio/files',

    batch_size = 1,

    data_max_length = 320 * 32,

    num_train_steps = 1

)

trainer.train()

```

After much training on all three transformers (semantic, coarse, fine), you will pass your finetuned or trained-from-scratch `AudioLM` and `MuLaN` wrapped in `MuLaNEmbedQuantizer` to the `MusicLM`

```python

musiclm = MusicLM(

        mulan_embed_quantizer: MuLaNEmbedQuantizer

    ):

        super().__init__()

        assert not exists(audio_lm.audio_conditioner), 'mulan must not have been passed into AudioLM. it will be managed externally now, embedding the text into the joint embedding space for text-to-audio synthesis'

        self.mulan_embed_quantizer = mulan_embed_quantizer

        self.audio_lm = audio_lm

setup(

  name = 'musiclm-pytorch',

  packages = find_packages(exclude=[]),

  version = '0.0.6',

  version = '0.0.7',

  license='MIT',

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

  author = 'Phil Wang',

    'contrastive learning'

  ],

  install_requires=[

    'audiolm-pytorch>=0.9.0',

    'audiolm-pytorch>=0.9.2',

    'beartype',

    'einops>=0.4',

    'vector-quantize-pytorch>=1.0.0',