Downloads · 30 days
65
22% of all-time downloads
Karthikappi0011/genshin-furina-english-qwen3-tts
genshin-furina-english-qwen3-tts is a text-to-speech model from Karthikappi0011. Use it when you need text read aloud.
This is a fine-tuned Custom Voice model for Qwen3-TTS, trained to sound like Furina from Genshin Impact (English voice). It uses the neural speech codec approach (12Hz) to generate highly expressive, high-fidelity spe…
Downloads · 30 days
65
22% of all-time downloads
All-time downloads
292
Public
Parameters
1.9B
4.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.5 GB · 100%
From the Hugging Face model README
This is a fine-tuned Custom Voice model for Qwen3-TTS, trained to sound like Furina from Genshin Impact (English voice). It uses the neural speech codec approach (12Hz) to generate highly expressive, high-fidelity speech.
First, ensure you have the qwen-tts package installed:
pip install qwen-tts torch soundfile
You can generate Furina's voice in just a few lines of code. Make sure to set speaker="furina" exactly as shown below:
import soundfile as sf
import torch
from qwen_tts import Qwen3TTSModel
# 1. Load the fine-tuned model
print("Loading model...")
model = Qwen3TTSModel.from_pretrained(
"Karthikappi0011/genshin-furina-english-qwen3-tts",
device_map="cuda", # Change to "cpu" or "mps" if on Mac
torch_dtype=torch.bfloat16,
attn_implementation="sdpa", # Or "flash_attention_2" if supported
)
# 2. Provide the text
text = "Fontaine's water is beautiful, don't you think? Witness my magnificence!"
# 3. Generate the audio
print("Generating audio...")
wavs, sr = model.generate_custom_voice(
text=text,
speaker="furina", # Must be "furina" to trigger the custom voice embedding
language="English", # Or "Auto"
)
# 4. Save to disk
output_path = "furina_output.wav"
sf.write(output_path, wavs[0], sr)
print(f"Saved generated speech to {output_path}")
furina