Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
facebook
/
seamless-m4t-v2-large
like
937
Follow
AI at Meta
10.5k
Automatic Speech Recognition
Transformers
Safetensors
96 languages
seamless_m4t_v2
feature-extraction
audio-to-audio
text-to-speech
seamless_communication
arxiv:
2312.05187
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
59
Deploy
Use this model
refs/pr/1
seamless-m4t-v2-large
20.6 GB
6 contributors
History:
12 commits
ylacombe
Upload processor
20e4b7c
about 2 years ago
.gitattributes
1.52 kB
Duplicate from meta-private/M4Tv2
about 2 years ago
README.md
12.4 kB
Update README.md
about 2 years ago
added_tokens.json
2.07 kB
Upload processor
about 2 years ago
m4t_v2_multitask_unity2.pt
11.4 GB
xet
Duplicate from meta-private/M4Tv2
about 2 years ago
preprocessor_config.json
1.78 kB
Upload processor
about 2 years ago
seamlessM4T_v2_large.pt
9.07 GB
xet
Duplicate from meta-private/M4Tv2
about 2 years ago
seamlessm4t_arch.svg
50.1 kB
Upload seamlessm4t_arch.svg
about 2 years ago
sentencepiece.bpe.model
5.17 MB
xet
Upload processor
about 2 years ago
special_tokens_map.json
2.34 kB
Upload processor
about 2 years ago
spm_char_lang38_tc.model
369 kB
xet
Duplicate from meta-private/M4Tv2
about 2 years ago
tokenizer.model
5.17 MB
xet
Duplicate from meta-private/M4Tv2
about 2 years ago
tokenizer_config.json
19.7 kB
Upload processor
about 2 years ago
vocoder_v2.pt
168 MB
xet
Duplicate from meta-private/M4Tv2
about 2 years ago
