Instructions to use gitgato/speech-ts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use gitgato/speech-ts with ESPnet:
from espnet2.bin.tts_inference import Text2Speech model = Text2Speech.from_pretrained("gitgato/speech-ts") speech, *_ = model("text to generate speech from") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,11 +4,15 @@ tags:
|
|
| 4 |
- audio
|
| 5 |
- text-to-speech
|
| 6 |
datasets:
|
| 7 |
-
-
|
|
|
|
| 8 |
base_model:
|
| 9 |
- microsoft/speecht5_tts
|
| 10 |
pipeline_tag: text-to-speech
|
| 11 |
-
library_name:
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# SpeechT5 (TTS task)
|
|
|
|
| 4 |
- audio
|
| 5 |
- text-to-speech
|
| 6 |
datasets:
|
| 7 |
+
- ovieyra21/mabama-v8
|
| 8 |
+
- ovieyra21/mabama-v9
|
| 9 |
base_model:
|
| 10 |
- microsoft/speecht5_tts
|
| 11 |
pipeline_tag: text-to-speech
|
| 12 |
+
library_name: adapter-transformers
|
| 13 |
+
metrics:
|
| 14 |
+
- charcut_mt
|
| 15 |
+
new_version: openai/whisper-large-v3-turbo
|
| 16 |
---
|
| 17 |
|
| 18 |
# SpeechT5 (TTS task)
|