Update README.md
Browse files
README.md
CHANGED
|
@@ -2,13 +2,16 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- zh
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
library_name: diffusers
|
| 8 |
pipeline_tag: text-to-image
|
| 9 |
tags:
|
| 10 |
- medical
|
| 11 |
-
-
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# Whisper
|
|
@@ -23,4 +26,4 @@ by Alec Radford et al. from OpenAI. The original code repository can be found [h
|
|
| 23 |
Whisper `large-v3` has the same architecture as the previous large models except the following minor differences:
|
| 24 |
|
| 25 |
1. The input uses 128 Mel frequency bins instead of 80
|
| 26 |
-
2. A new language token for Cantonese
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- zh
|
| 5 |
+
- aa
|
| 6 |
+
- af
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
library_name: diffusers
|
| 10 |
pipeline_tag: text-to-image
|
| 11 |
tags:
|
| 12 |
- medical
|
| 13 |
+
- code
|
| 14 |
+
- suibian
|
| 15 |
---
|
| 16 |
|
| 17 |
# Whisper
|
|
|
|
| 26 |
Whisper `large-v3` has the same architecture as the previous large models except the following minor differences:
|
| 27 |
|
| 28 |
1. The input uses 128 Mel frequency bins instead of 80
|
| 29 |
+
2. A new language token for Cantonese
|