Downloads · 30 days
157
0% of all-time downloads
ellie-Bert-VITS2
BricksDisplay/ellie-Bert-VITS2
ellie-Bert-VITS2 is a text-to-speech model from BricksDisplay. Use it when you need text read aloud. It is set up for transformers. The card lists the license as cc-by-4.0.
All-time downloads
80.2K
Public
Parameters
397M
6.5 GB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.onnx2 GB · 56%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- License
- cc-by-4.0
- Model type
- bert_vits2
- Access
- Public
- Created
- Jun 13, 2024
- Updated
- Aug 13, 2026
- SHA
- 3efd2588
Base models
Spaces
Model card
From the Hugging Face model README
Taiwan accent TTS model from JackEllie.
Usage
Using this checkpoint from Hugging Face Transformers:
from transformers import AutoModel, AutoProcessor
from scipy.io.wavfile import write
import torch
model_name = "BricksDisplay/ellie-Bert-VITS2"
model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
with torch.no_grad():
inputs = processor("你好", language="zh", return_tensors="pt")
result = model(**inputs)
result = result["waveform"]
write("output.wav", model.config.sampling_rate, result[0].numpy())
- Task
- Text-to-Speech
- Library
- transformers
- Type
- bert_vits2
- License
- cc-by-4.0
- Languages
- zh
- Created
- Jun 13, 2024
- Updated
- Aug 13, 2026