Hugging Face's logo

Juicesyo
/
Spark-TTS-Encore

Text-to-Speech
Transformers
Safetensors
Chinese
qwen2
text-generation
unsloth
text-generation-inference
Model card Files
xet
 Community
How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-to-speech", model="Juicesyo/Spark-TTS-Encore")
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Juicesyo/Spark-TTS-Encore")
model = AutoModelForCausalLM.from_pretrained("Juicesyo/Spark-TTS-Encore")
Quick Links

Model Card for Model ID

This is a TTS model fine-tuned based on Spark-TTS-0.5B.

Model Description

  • Fine-tune dataset: [Juicesyo/WutheringWaves-Encore-voice-zh]
  • Language(s) (NLP): [Chinese]
  • Finetuned from model: [Spark-TTS-0.5B]
Downloads last month
2
Safetensors
Model size
0.5B params
Tensor type
F32
·
Inference Providers NEW
Text-to-Speech
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Juicesyo/Spark-TTS-Encore

Base model

SparkAudio/Spark-TTS-0.5B
Finetuned
(25)
this model

Dataset used to train Juicesyo/Spark-TTS-Encore