Codesota · Models · VoiceboxMeta AI2 results · 2 benchmarks
Model card

Voicebox.

Meta AIproprietary330M paramsFlow matching (non-autoregressive)

Le et al. arXiv 2306.15687.

§ 01 · Benchmarks

Every benchmark Voicebox has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01LibriTTS test-clean (Zero-Shot TTS)Speech · Voice Cloningwer1.9%#2/3source ↗
02LJ SpeechSpeech · Text-to-Speechmos4.3%#4/52023-06-27source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where Voicebox actually performs.

Speech
2
benchmarks
avg rank #3.0
§ 03 · Papers

1 paper with results for Voicebox.

  1. 2023-06-27· Speech· 1 result

    Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

§ 04 · Related models

Other Meta AI models scored on Codesota.

GENRE
1 result · 1 SOTA
SeamlessM4T v2 Large
2.3B params · 1 result · 1 SOTA
DINOv2 (ViT-g) + Linear
Unknown params · 1 result
Fairseq S2T (MuST-C)
~150M params · 1 result
Mask2Former (Swin-L)
Unknown params · 1 result
MusicGen Large
3.3B params · 1 result
convnext_base.fb_in22k_ft_in1k
1 result
ConvNeXt V2-H
0 results
§ 05 · Sources & freshness

Where these numbers come from.

editorial
1
result
arxiv
1
result
1 of 2 rows marked verified.