---
language:
- hi
- en
license: apache-2.0
datasets:
- navneetjais/Navjeet
library_name: transformers
tags:
  - text-to-speech
  - audio
  - tts
  - unsloth
pipeline_tag: text-to-speech
base_model: canopylabs/orpheus-3b-0.1-pretrained
---
# Navjeet – Fine-tuned Orpheus 3B TTS

This model converts text into speech using the Orpheus 3B architecture fine-tuned with Unsloth.

## 🧠 How to use
```python
from transformers import pipeline
import os

# Set the Hugging Face token as an environment variable if you have one
# os.environ["HF_TOKEN"] = "YOUR_HF_TOKEN" # Replace with your token

tts = pipeline("text-to-speech", model="navneetjais/Navjeet")
audio = tts("Namaste, yah Navjeet bol raha hai!")
print(audio)
with open("output.wav", "wb") as f:
    f.write(audio["audio"])

from IPython.display import Audio
Audio(audio["audio"], rate=audio["sampling_rate"])