Text-to-Speech
Transformers
Safetensors
higgs_multimodal_qwen3
text-generation
speech-generation
higgs-audio
qwen3
quantization
4-bit precision
awq
Instructions to use Reza2kn/Higgs-Audio-v3-TTS-4bit-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Reza2kn/Higgs-Audio-v3-TTS-4bit-AWQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Reza2kn/Higgs-Audio-v3-TTS-4bit-AWQ")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("Reza2kn/Higgs-Audio-v3-TTS-4bit-AWQ", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model": "bosonai/higgs-audio-v3-tts-4b", | |
| "base_model_relation": "quantized", | |
| "format": "awq", | |
| "quantized_scope": "body.layers.* 2D transformer weights only", | |
| "preserved_scope": "codec/vocoder, fused modality embedding/head, norms, biases, non-2D tensors", | |
| "quantized_parameters": 3633315840, | |
| "total_parameters_seen": 4654850537, | |
| "quantized_parameter_fraction": 0.780544039195216, | |
| "artifact_note": "Runtime integration required for Higgs custom multi-codebook TTS generation." | |
| } | |