Update README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,12 @@ SeamlessM4T models support the tasks of:
|
|
13 |
- Text-to-text translation (T2TT)
|
14 |
- Automatic speech recognition (ASR).
|
15 |
|
16 |
-
|
|
|
|
|
|
|
|
|
|
|
17 |
This new model improves over SeamlessM4T v1 in quality as well as inference speed in speech generation tasks.
|
18 |
|
19 |
The v2 version of SeamlessM4T is a multitask adaptation of our novel *UnitY2* architecture.
|
|
|
13 |
- Text-to-text translation (T2TT)
|
14 |
- Automatic speech recognition (ASR).
|
15 |
|
16 |
+
SeamlessM4T models support:
|
17 |
+
- 🎤 101 languages for speech input.
|
18 |
+
- 💬 96 Languages for text input/output.
|
19 |
+
- 🔊 35 languages for speech output.
|
20 |
+
|
21 |
+
🌟 We are releasing SemalessM4T v2, an updated version with our novel *UnitY2* architecture.
|
22 |
This new model improves over SeamlessM4T v1 in quality as well as inference speed in speech generation tasks.
|
23 |
|
24 |
The v2 version of SeamlessM4T is a multitask adaptation of our novel *UnitY2* architecture.
|