Add pipeline_tag: audio-to-audio to metadata
Browse filesThis PR adds the `pipeline_tag: audio-to-audio` metadata to your model card. This will help users discover your speech editing model more easily when filtering by task on the Hugging Face Hub.
README.md
CHANGED
|
@@ -1,15 +1,17 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
datasets:
|
| 5 |
- CJY/GigaEdit-S
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
-
|
| 9 |
-
|
|
|
|
| 10 |
tags:
|
| 11 |
- Speech Editing
|
| 12 |
---
|
|
|
|
| 13 |
# CosyEdit: Unlocking End-to-End Speech Editing Capability from Zero-Shot Text-to-Speech Models
|
| 14 |
|
| 15 |
## Highlight 🔥
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- FunAudioLLM/CosyVoice-300M
|
| 4 |
datasets:
|
| 5 |
- CJY/GigaEdit-S
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
+
library_name: cosyvoice
|
| 9 |
+
license: apache-2.0
|
| 10 |
+
pipeline_tag: audio-to-audio
|
| 11 |
tags:
|
| 12 |
- Speech Editing
|
| 13 |
---
|
| 14 |
+
|
| 15 |
# CosyEdit: Unlocking End-to-End Speech Editing Capability from Zero-Shot Text-to-Speech Models
|
| 16 |
|
| 17 |
## Highlight 🔥
|