facebook
/

hf-seamless-m4t-medium

feature-extraction

Inference Endpoints

Model card Files Files and versions Community

ylacombe HF staff commited on Sep 19, 2023

Commit

2ad3661

•

1 Parent(s): b61a560

Update README.md

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-inference: false
 tags:
 - SeamlessM4T
 - seamless_m4t
@@ -14,8 +14,8 @@ linguistic communities to communicate effortlessly through speech and text.
 SeamlessM4T covers:
 - 📥 101 languages for speech input
-- ⌨️ 96 Languages for text input/output
-- 🗣️ 35 languages for speech output.
 This is the "medium" variant of the unified model, which enables multiple tasks without relying on multiple separate models:
 - Speech-to-speech translation (S2ST)
@@ -27,7 +27,6 @@ This is the "medium" variant of the unified model, which enables multiple tasks
 You can perform all the above tasks from one single model - `SeamlessM4TModel`, but each task also has its own dedicated sub-model.
 ## Usage
 First, load the processor and a checkpoint of the model:

 ---
+inference: true
 tags:
 - SeamlessM4T
 - seamless_m4t
 SeamlessM4T covers:
 - 📥 101 languages for speech input
+- ⌨️ [196 Languages](https://huggingface.co/ylacombe/hf-seamless-m4t-medium/blob/main/tokenizer_config.json#L1887-L2089) for text input/output
+- 🗣️ [35 languages](https://huggingface.co/ylacombe/hf-seamless-m4t-medium/blob/main/generation_config.json#L253-L288) for speech output.
 This is the "medium" variant of the unified model, which enables multiple tasks without relying on multiple separate models:
 - Speech-to-speech translation (S2ST)
 You can perform all the above tasks from one single model - `SeamlessM4TModel`, but each task also has its own dedicated sub-model.
 ## Usage
 First, load the processor and a checkpoint of the model: