Text-to-Speech
Transformers
Safetensors
Fast_dLLM_Qwen
text-generation
audio
speech
speech-language-models
custom_code
Instructions to use ssonpull519/neutts-air-dllm-bd8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ssonpull519/neutts-air-dllm-bd8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="ssonpull519/neutts-air-dllm-bd8", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ssonpull519/neutts-air-dllm-bd8", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)
NeuTTS Air dLLM
NeuTTS Air model which is further trained unofficially for block-causal generation capability.
All the credits and license for the amazing base NeuTTS model from NeuTTS-Air.
Modeling and configuration implementation is heavily borrowed from Fast-dLLM, so it can be easily train based on their codes if you want.
For brief summary of what is done, refer to my post.
Usage
Please refer to repository for local inference.
- Downloads last month
- 3