audiolm

library0.0.1.dev0pypypi✓ verified 81d ago

AudioLM is a PyTorch-based implementation of a language modeling approach to audio generation, capable of generating coherent audio continuations given a short prompt. Current version is 0.0.1.dev0, with irregular releases.

ai-ml

pip install audiolm

package ↗

INSTALL

IMPORT

SIG · AUDIOLM

audiolm

ai-mlpythonv0.0.1.dev0

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

AudioLM

✓ import audiolm

✗ from audiolm import AudioLM

Load a pre-trained AudioLM model and generate a continuation from a prompt audio file.

import torch import torchaudio from audiolm import AudioLM from audiolm.decode import decode model = AudioLM() # Load a prompt audio file waveform, sample_rate = torchaudio.load('prompt.wav') # Generate continuation (requires GPU or CPU) generated = decode(model, waveform, sample_rate, max_new_tokens=256) torchaudio.save('output.wav', generated[0].unsqueeze(0), sample_rate)

Debug

Known issues

breakingThe library is in early development (0.0.1.dev0). API is unstable and may change without notice. Do not use in production.

fix

Pin to specific commit or use only for experimentation.

affects: all

gotchaAudioLM requires significant GPU memory (16GB+). CPU inference is extremely slow and may run out of memory.

fix

Use a GPU with at least 16GB VRAM; reduce max_new_tokens if out-of-memory.

affects: all

deprecatedThe 'decode' function signature may change in future versions; current version uses (model, waveform, sample_rate, ...).

fix

Refer to the GitHub README for the most up-to-date usage.

affects: 0.0.1.dev0

Upgrade

Version history

0.0.1.dev0latest on PyPI · released Mar 26, 2023

Audit

Dependencies

torchrequiredCore dependency for model operations

torchaudiorequiredAudio I/O and processing

transformersrequiredHuggingFace models and tokenizers

soundfilerequiredAudio file reading/writing

einopsrequiredTensor operations

Agent activity

16 hits · last 30 days

node

OpenAI (training)

Resources

packagehttps://pypi.org/project/audiolm/ ↗