Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
inference:
|
| 3 |
tags:
|
| 4 |
- SeamlessM4T
|
| 5 |
- seamless_m4t
|
|
@@ -14,8 +14,8 @@ linguistic communities to communicate effortlessly through speech and text.
|
|
| 14 |
|
| 15 |
SeamlessM4T covers:
|
| 16 |
- 📥 101 languages for speech input
|
| 17 |
-
- ⌨️
|
| 18 |
-
- 🗣️ 35 languages for speech output.
|
| 19 |
|
| 20 |
This is the "medium" variant of the unified model, which enables multiple tasks without relying on multiple separate models:
|
| 21 |
- Speech-to-speech translation (S2ST)
|
|
@@ -27,7 +27,6 @@ This is the "medium" variant of the unified model, which enables multiple tasks
|
|
| 27 |
You can perform all the above tasks from one single model - `SeamlessM4TModel`, but each task also has its own dedicated sub-model.
|
| 28 |
|
| 29 |
|
| 30 |
-
|
| 31 |
## Usage
|
| 32 |
|
| 33 |
First, load the processor and a checkpoint of the model:
|
|
|
|
| 1 |
---
|
| 2 |
+
inference: true
|
| 3 |
tags:
|
| 4 |
- SeamlessM4T
|
| 5 |
- seamless_m4t
|
|
|
|
| 14 |
|
| 15 |
SeamlessM4T covers:
|
| 16 |
- 📥 101 languages for speech input
|
| 17 |
+
- ⌨️ [196 Languages](https://huggingface.co/ylacombe/hf-seamless-m4t-medium/blob/main/tokenizer_config.json#L1887-L2089) for text input/output
|
| 18 |
+
- 🗣️ [35 languages](https://huggingface.co/ylacombe/hf-seamless-m4t-medium/blob/main/generation_config.json#L253-L288) for speech output.
|
| 19 |
|
| 20 |
This is the "medium" variant of the unified model, which enables multiple tasks without relying on multiple separate models:
|
| 21 |
- Speech-to-speech translation (S2ST)
|
|
|
|
| 27 |
You can perform all the above tasks from one single model - `SeamlessM4TModel`, but each task also has its own dedicated sub-model.
|
| 28 |
|
| 29 |
|
|
|
|
| 30 |
## Usage
|
| 31 |
|
| 32 |
First, load the processor and a checkpoint of the model:
|