Text-to-Speech
Transformers
Safetensors
arktts
feature-extraction
audio
tts
voice-cloning
zero-shot
multilingual
custom_code
Instructions to use Audio8/Audio8-TTS-Preview-0.1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Audio8/Audio8-TTS-Preview-0.1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Audio8/Audio8-TTS-Preview-0.1b", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Audio8/Audio8-TTS-Preview-0.1b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "ArkttsModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_in_multiplier": 1.0, | |
| "attention_o_bias": false, | |
| "attention_out_multiplier": 1.0, | |
| "attention_qk_norm": false, | |
| "attention_qkv_bias": false, | |
| "auto_map": { | |
| "AutoConfig": "configuration_arktts.ArkttsConfig", | |
| "AutoModel": "modeling_arktts.ArkttsModel", | |
| "AutoModelForCausalLM": "modeling_arktts.ArkttsModel" | |
| }, | |
| "bos_token_id": 17, | |
| "codebook_size": 4096, | |
| "codec_filename": "codec.pth", | |
| "codec_frame_size": 2048, | |
| "codec_post_intermediate_size": 1216, | |
| "codec_post_n_head": 16, | |
| "codec_post_n_layer": 8, | |
| "codec_post_n_local_heads": 8, | |
| "codec_sample_rate": 44100, | |
| "dim": 512, | |
| "dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "embedding_multiplier": 0.10888671875, | |
| "eos_token_id": 228, | |
| "expansion_factor": 1.5, | |
| "fast_attention_o_bias": false, | |
| "fast_attention_qk_norm": false, | |
| "fast_attention_qkv_bias": false, | |
| "fast_dim": 512, | |
| "fast_head_dim": 64, | |
| "fast_intermediate_size": 4864, | |
| "fast_n_head": 8, | |
| "fast_n_local_heads": 2, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 768, | |
| "key_multiplier": 1.0, | |
| "lm_head_multiplier": 0.078125, | |
| "mamba_chunk_size": 128, | |
| "mamba_conv_bias": true, | |
| "mamba_d_conv": 4, | |
| "mamba_d_head": 32, | |
| "mamba_d_ssm": 768, | |
| "mamba_d_state": 64, | |
| "mamba_expand": 2, | |
| "mamba_n_groups": 1, | |
| "mamba_n_heads": 24, | |
| "mamba_norm_before_gate": false, | |
| "mamba_proj_bias": false, | |
| "mamba_rms_norm": false, | |
| "mamba_use_mlp": true, | |
| "max_position_embeddings": 8192, | |
| "max_seq_len": 2048, | |
| "mlp_bias": false, | |
| "mlp_multipliers": [ | |
| 1.0, | |
| 1.0 | |
| ], | |
| "model_type": "arktts", | |
| "n_fast_layer": 4, | |
| "n_head": 8, | |
| "n_layer": 24, | |
| "n_local_heads": 2, | |
| "norm_eps": 1e-05, | |
| "norm_fastlayer_input": false, | |
| "num_attention_heads": 8, | |
| "num_codebooks": 10, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "num_logits_to_keep": 1, | |
| "pad_token_id": 0, | |
| "projectors_bias": false, | |
| "ras_temperature": 1.0, | |
| "ras_top_p": 0.9, | |
| "ras_window_size": 10, | |
| "rms_norm_eps": 1e-05, | |
| "rope_base": 100000000000.0, | |
| "rope_theta": 100000000000.0, | |
| "semantic_begin_id": 65537, | |
| "semantic_end_id": 69632, | |
| "slow_backbone": "falcon_h1", | |
| "ssm_in_multiplier": 1.0, | |
| "ssm_multipliers": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "ssm_out_multiplier": 1.0, | |
| "time_step_floor": 0.0001, | |
| "time_step_max": 0.1, | |
| "time_step_min": 0.001, | |
| "time_step_rank": "auto", | |
| "transformers_version": "4.57.5", | |
| "use_cache": true, | |
| "use_gradient_checkpointing": false, | |
| "vocab_size": 69633 | |
| } | |