Text-to-Speech
Transformers
Safetensors
English
higgs_multimodal_qwen3
feature-extraction
tts
voice-cloning
higgs-audio
qwen3
custom_code
Instructions to use Infinix-io/back-up-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Infinix-io/back-up-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Infinix-io/back-up-1", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Infinix-io/back-up-1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from Infinix-io/back-up-1: direct link, hf CLI and curl.
- Browser
- Download file 1.73 kB
-
https://huggingface.co/Infinix-io/back-up-1/resolve/main/config.json
- Command line
-
hf download hf://Infinix-io/back-up-1/config.json
-
curl -L -o config.json https://huggingface.co/Infinix-io/back-up-1/resolve/main/config.json
1.73 kB
| { | |
| "architectures": [ | |
| "HiggsMultimodalQwen3ForConditionalGeneration" | |
| ], | |
| "model_type": "higgs_multimodal_qwen3", | |
| "auto_map": { | |
| "AutoConfig": "configuration_higgs_multimodal_qwen3.HiggsMultimodalQwen3Config", | |
| "AutoModel": "modeling_higgs_multimodal_qwen3.HiggsMultimodalQwen3ForConditionalGeneration", | |
| "AutoModelForCausalLM": "modeling_higgs_multimodal_qwen3.HiggsMultimodalQwen3ForConditionalGeneration" | |
| }, | |
| "audio_token_id": -100, | |
| "ignore_index": -100, | |
| "mel_per_sample": 8, | |
| "sample_rate": 24000, | |
| "audio_tokenizer_id": "bosonai/higgs-audio-v2-tokenizer", | |
| "audio_encoder_config": { | |
| "encoder_type": "discrete", | |
| "mel_per_sample": 8, | |
| "model_type": "higgs_audio_encoder", | |
| "num_codebooks": 8, | |
| "out_dim": 2560, | |
| "tie_word_embeddings": true, | |
| "use_delay_pattern": true, | |
| "vocab_size": 1026 | |
| }, | |
| "text_config": { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151643, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "dtype": "bfloat16", | |
| "transformers_version": "5.5.0" | |
| } | |