| --- |
| library_name: transformers |
| license: other |
| tags: |
| - audio |
| - audio-codec |
| - pytorch |
| - bfloat16 |
| --- |
| |
| # Liquid Codec BF16 |
|
|
| ## Remote-code loading |
|
|
| The repository includes the codec configuration and model implementation, so it can be loaded with `AutoModel`: |
|
|
| ```python |
| import torch |
| from transformers import AutoModel |
| |
| codec = AutoModel.from_pretrained( |
| "LiquidAI/Liquid-Codec", |
| trust_remote_code=True, |
| dtype=torch.bfloat16, |
| device_map="cuda", |
| ) |
| waveform = torch.randn(1, 24_000 * 3, device="cuda") # 24 kHz |
| codes = codec.encode(waveform).audio_codes |
| reconstructed = codec.decode(codes).audio_values |
| ``` |
|
|
| ## Native loading and streaming |
|
|
| ```python |
| import torch |
| from transformers import LiquidCodecModel, LiquidCodecStreamingCache |
| |
| codec = LiquidCodecModel.from_pretrained("LiquidAI/Liquid-Codec", dtype=torch.bfloat16, device_map="cuda") |
| |
| waveform = torch.randn(1, 24_000 * 3, device="cuda") # 24 kHz |
| codes = codec.encode(waveform).audio_codes # (1, 12, 38) |
| reconstructed = codec.decode(codes).audio_values # (1, 38 * 1920), float32 |
| |
| # streaming synthesis: every chunk returns the samples that no later frame changes any more |
| cache = LiquidCodecStreamingCache(codec.config) |
| chunks = [codec.decode(codes[..., i : i + 1], cache, finalize=False).audio_values for i in range(codes.shape[-1])] |
| chunks.append(codec.decode(codes[..., :0], cache, finalize=True).audio_values) |
| streamed = torch.cat(chunks, dim=-1) |
| ``` |
|
|
