facebook/seamless-m4t-v2-large

Automatic Speech Recognition • Updated Jan 4 • 66.9k • 710

Note SemalessM4T v2, an updated version with our novel UnitY2 architecture. This new model improves over SeamlessM4T v1 in quality as well as inference latency in speech generation tasks.

facebook/seamless-expressive

Text-to-Speech • Updated Jan 4 • 171

Note SeamlessExpressive is a speech-to-speech translation model that captures certain underexplored aspects of prosody such as speech rate and pauses, while preserving the style of one's voice and high content translation quality.

facebook/seamless-streaming

Text-to-Speech • Updated Jan 4 • 204

Note SeamlessStreaming is a streaming translation model. The model supports speech as input modality and speech/text as output modalities.

facebook/hf-seamless-m4t-large

Text-to-Speech • Updated Dec 8, 2023 • 1.93k • 56

Note A 2.3B version designed for speech-to-speech translation (S2ST), speech-to-text translation (S2TT), text-to-speech translation (T2ST), text-to-text translation (T2TT) and automatic speech recognition (ASR). Transformers implementation of SeamlessM4T-large

facebook/hf-seamless-m4t-medium

Text-to-Speech • Updated Dec 8, 2023 • 15.3k • 29

Note A 1.2B version also designed for S2ST, S2TT, T2ST, T2TT and ASR. Transformers implementation of SeamlessM4T-medium

facebook/seamless-m4t-large

Automatic Speech Recognition • Updated Dec 14, 2023 • 510

Note A 2.3B version designed for speech-to-speech translation (S2ST), speech-to-text translation (S2TT), text-to-speech translation (T2ST), text-to-text translation (T2TT) and automatic speech recognition (ASR).

facebook/seamless-m4t-medium

Automatic Speech Recognition • Updated Dec 14, 2023 • 128

Note A 1.2B version also designed for S2ST, S2TT, T2ST, T2TT and ASR.

facebook/seamless-m4t-unity-small-s2t

Updated Aug 24, 2023 • 28

Note Designed for on-device inference (S2TT, S2ST, ASR).

facebook/seamless-m4t-unity-small

Updated Aug 24, 2023 • 29

Note Designed for on-device inference (S2TT, ASR).