Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
tags:
|
| 4 |
+
- text-to-speech
|
| 5 |
+
- tts
|
| 6 |
+
- audio
|
| 7 |
+
- speech-synthesis
|
| 8 |
+
- orpheus
|
| 9 |
+
- awq
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
datasets:
|
| 12 |
+
- internal
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Orpheus-3b-FT-AWQ
|
| 16 |
+
|
| 17 |
+
This is a quantised version of [canopylabs/orpheus-3b-0.1-ft](https://huggingface.co/canopylabs/orpheus-3b-0.1-ft).
|
| 18 |
+
|
| 19 |
+
Orpheus is a high-performance Text-to-Speech model fine-tuned for natural, emotional speech synthesis. This repository hosts the 8-bit quantised version of the 3B parameter model, optimised for efficiency while maintaining high-quality output.
|
| 20 |
+
|
| 21 |
+
## Model Description
|
| 22 |
+
|
| 23 |
+
**Orpheus-3b-FT-AWQ** is a 3 billion parameter Text-to-Speech model that converts text inputs into natural-sounding speech with support for multiple voices and emotional expressions. The model has been quantised to 8-bit (Q8_0) format for efficient inference, making it accessible on consumer hardware.
|
| 24 |
+
|
| 25 |
+
Key features:
|
| 26 |
+
- 8 distinct voice options with different characteristics
|
| 27 |
+
- Support for emotion tags like laughter, sighs, etc.
|
| 28 |
+
- Optimised for CUDA acceleration on RTX GPUs
|
| 29 |
+
- Produces high-quality 24kHz mono audio
|
| 30 |
+
- Fine-tuned for conversational naturalness
|