Text-to-Speech
Transformers
Safetensors
Qwen3-TTS
English
text-generation
tts
prompttts
qwen3-tts
voice-design
vocence
british-english
uk-accent
Instructions to use matthewliu0302/grit_v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use matthewliu0302/grit_v4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="matthewliu0302/grit_v4")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("matthewliu0302/grit_v4", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| # Miner + /health metadata. Weights live in this HF repo (no runtime model_id). | |
| # Required: must match the model_name committed on chain. | |
| model_name: "matthewliu0302/grit_v4" | |
| runtime: | |
| adapter: "qwen3_tts_repo_snapshot" | |
| device_preference: "cuda" | |
| dtype: "bfloat16" | |
| default_language: "English" | |
| use_flash_attention_2: false | |
| generation: | |
| sample_rate: 24000 | |
| max_seconds: 30 | |
| limits: | |
| max_text_chars: 2000 | |
| max_instruction_chars: 600 | |
| default_language: "English" | |