SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.15687 · NeurIPS · 2023

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

Yossi Adi, Apoorv Vyas, Bowen Shi, Wei-Ning Hsu, Matthew Le, Brian Karrer, Leda Sari, Rashel Moritz, Mary Williamson, Vimal Manohar, Jay Mahadeokar

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 10 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
lucidrains/voicebox-pytorch pwc_unofficial 10 of 10
FunctionStatusWhere it lives
cast_tuple Ran lucidrains/voicebox-pytorch/voicebox_pytorch/data.py
code served (permissive licence) · get_code("f70dcb896366697c")
cast_tuple Ran lucidrains/voicebox-pytorch/voicebox_pytorch/trainer.py
code served (permissive licence) · get_code("5cfcc1d3230706ff")
collate_one_or_multiple_tensors Ran lucidrains/voicebox-pytorch/voicebox_pytorch/data.py
code served (permissive licence) · get_code("0e0470ad1da271f6")
default Ran lucidrains/voicebox-pytorch/voicebox_pytorch/attend.py
code served (permissive licence) · get_code("60fff7c3c400d7ff")
exists Ran lucidrains/voicebox-pytorch/voicebox_pytorch/attend.py
code served (permissive licence) · get_code("aa5486a3650902d8")
get_optimizer Ran lucidrains/voicebox-pytorch/voicebox_pytorch/optimizer.py
code served (permissive licence) · get_code("9354ff16b3840873")
identity Ran lucidrains/voicebox-pytorch/voicebox_pytorch/voicebox_pytorch.py
code served (permissive licence) · get_code("f3232418205f7cbd")
once Ran lucidrains/voicebox-pytorch/voicebox_pytorch/attend.py
code served (permissive licence) · get_code("52e10a7d6b0fa036")
separate_weight_decayable_params Ran lucidrains/voicebox-pytorch/voicebox_pytorch/optimizer.py
code served (permissive licence) · get_code("fdc11aefc97f3abb")
yes_or_no Ran lucidrains/voicebox-pytorch/voicebox_pytorch/trainer.py
code served (permissive licence) · get_code("d95562c398a6b25e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large-scale generative models such as GPT and DALL-E have revolutionized natural language processing and computer vision research. These models not only generate high fidelity text or image outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are neither filtered nor enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster. Audio samples can be found in https://voicebox.metademolab.com.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2306.15687")
get_code_for_paper("2306.15687")
have("2306.15687")

Connect an agent — have() is free.