Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,6 @@ tags:
|
|
| 22 |
# VITS TTS for Indian Languages
|
| 23 |
|
| 24 |
This repository contains a VITS-based Text-to-Speech (TTS) model fine-tuned for Indian languages. The model supports multiple Indian languages and a wide range of speaking styles and emotions, making it suitable for diverse use cases such as conversational AI, audiobooks, and more.
|
| 25 |
-
|
| 26 |
---
|
| 27 |
|
| 28 |
## Model Overview
|
|
@@ -31,7 +30,6 @@ The model `ai4bharat/vits_rasa_13` is based on the VITS architecture and support
|
|
| 31 |
- **Languages**: Multiple Indian languages.
|
| 32 |
- **Styles**: Various speaking styles and emotions.
|
| 33 |
- **Speaker IDs**: Predefined speaker profiles for male and female voices.
|
| 34 |
-
|
| 35 |
---
|
| 36 |
|
| 37 |
## Installation
|
|
@@ -39,7 +37,6 @@ The model `ai4bharat/vits_rasa_13` is based on the VITS architecture and support
|
|
| 39 |
```bash
|
| 40 |
pip install transformers torch
|
| 41 |
```
|
| 42 |
-
|
| 43 |
---
|
| 44 |
|
| 45 |
## Usage
|
|
@@ -62,7 +59,6 @@ outputs = model(inputs['input_ids'], speaker_id=speaker_id, emotion_id=style_id)
|
|
| 62 |
sf.write("audio.wav", outputs.waveform.squeeze(), model.config.sampling_rate)
|
| 63 |
print(outputs.waveform.shape)
|
| 64 |
```
|
| 65 |
-
|
| 66 |
---
|
| 67 |
|
| 68 |
## Supported Languages
|
|
@@ -80,7 +76,6 @@ print(outputs.waveform.shape)
|
|
| 80 |
- `Sanskrit`
|
| 81 |
- `Tamil`
|
| 82 |
- `Telugu`
|
| 83 |
-
|
| 84 |
---
|
| 85 |
|
| 86 |
## Speaker-Style Identifier Overview
|
|
@@ -238,7 +233,6 @@ print(outputs.waveform.shape)
|
|
| 238 |
</table>
|
| 239 |
|
| 240 |
</div>
|
| 241 |
-
|
| 242 |
---
|
| 243 |
|
| 244 |
## Citation
|
|
|
|
| 22 |
# VITS TTS for Indian Languages
|
| 23 |
|
| 24 |
This repository contains a VITS-based Text-to-Speech (TTS) model fine-tuned for Indian languages. The model supports multiple Indian languages and a wide range of speaking styles and emotions, making it suitable for diverse use cases such as conversational AI, audiobooks, and more.
|
|
|
|
| 25 |
---
|
| 26 |
|
| 27 |
## Model Overview
|
|
|
|
| 30 |
- **Languages**: Multiple Indian languages.
|
| 31 |
- **Styles**: Various speaking styles and emotions.
|
| 32 |
- **Speaker IDs**: Predefined speaker profiles for male and female voices.
|
|
|
|
| 33 |
---
|
| 34 |
|
| 35 |
## Installation
|
|
|
|
| 37 |
```bash
|
| 38 |
pip install transformers torch
|
| 39 |
```
|
|
|
|
| 40 |
---
|
| 41 |
|
| 42 |
## Usage
|
|
|
|
| 59 |
sf.write("audio.wav", outputs.waveform.squeeze(), model.config.sampling_rate)
|
| 60 |
print(outputs.waveform.shape)
|
| 61 |
```
|
|
|
|
| 62 |
---
|
| 63 |
|
| 64 |
## Supported Languages
|
|
|
|
| 76 |
- `Sanskrit`
|
| 77 |
- `Tamil`
|
| 78 |
- `Telugu`
|
|
|
|
| 79 |
---
|
| 80 |
|
| 81 |
## Speaker-Style Identifier Overview
|
|
|
|
| 233 |
</table>
|
| 234 |
|
| 235 |
</div>
|
|
|
|
| 236 |
---
|
| 237 |
|
| 238 |
## Citation
|