Update README.md
Browse files
README.md
CHANGED
|
@@ -31,7 +31,7 @@ license: cc-by-nc-sa-4.0
|
|
| 31 |
YarnGPT-local is a text-to-speech (TTS) model designed to synthesize Yoruba, Igbo and Hausa leveraging pure language modelling without external adapters or complex architectures, offering high-quality, natural, and culturally relevant speech synthesis for diverse applications.
|
| 32 |
|
| 33 |
|
| 34 |
-
#### How to use (Colab)
|
| 35 |
The model can generate audio on its own but its better to use a voice to prompt the model, there are about 10 voices supported by default:
|
| 36 |
- hausa_female1
|
| 37 |
- hausa_female2
|
|
@@ -44,7 +44,7 @@ The model can generate audio on its own but its better to use a voice to prompt
|
|
| 44 |
- yoruba_female2
|
| 45 |
- yoruba_male2
|
| 46 |
|
| 47 |
-
|
| 48 |
```python
|
| 49 |
# clone the YarnGPT repo to get access to the `audiotokenizer`
|
| 50 |
!git clone https://github.com/saheedniyi02/yarngpt.git
|
|
|
|
| 31 |
YarnGPT-local is a text-to-speech (TTS) model designed to synthesize Yoruba, Igbo and Hausa leveraging pure language modelling without external adapters or complex architectures, offering high-quality, natural, and culturally relevant speech synthesis for diverse applications.
|
| 32 |
|
| 33 |
|
| 34 |
+
#### How to use (on Google Colab)
|
| 35 |
The model can generate audio on its own but its better to use a voice to prompt the model, there are about 10 voices supported by default:
|
| 36 |
- hausa_female1
|
| 37 |
- hausa_female2
|
|
|
|
| 44 |
- yoruba_female2
|
| 45 |
- yoruba_male2
|
| 46 |
|
| 47 |
+
### Prompt YarnGPT-local
|
| 48 |
```python
|
| 49 |
# clone the YarnGPT repo to get access to the `audiotokenizer`
|
| 50 |
!git clone https://github.com/saheedniyi02/yarngpt.git
|