Text-to-Speech
Transformers
Safetensors
English
Chinese
arkasr
text-generation
automatic-speech-recognition
voice-conversion
speech
audio
custom_code
Instructions to use AutoArk-AI/GPA-v1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AutoArk-AI/GPA-v1.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="AutoArk-AI/GPA-v1.5", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("AutoArk-AI/GPA-v1.5", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "adapter_type": "mlp", | |
| "architectures": [ | |
| "ArkasrForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "audio_token_id": 151663, | |
| "auto_map": { | |
| "AutoConfig": "configuration_arkasr.ArkasrConfig", | |
| "AutoModelForCausalLM": "modeling_arkasr.ArkasrForConditionalGeneration" | |
| }, | |
| "dtype": "float32", | |
| "eos_token_id": 151665, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "max_whisper_length": 1500, | |
| "max_window_layers": 24, | |
| "merge_factor": 4, | |
| "mlp_adapter_act": "gelu", | |
| "model_type": "arkasr", | |
| "num_attention_heads": 14, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 151643, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "spec_aug": false, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "4.57.3", | |
| "use_cache": false, | |
| "use_mrope": false, | |
| "use_rope": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 163958, | |
| "whisper_config": { | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "apply_spec_augment": false, | |
| "architectures": [ | |
| "WhisperForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50257 | |
| ], | |
| "bos_token_id": 50257, | |
| "classifier_proj_size": 256, | |
| "d_model": 1280, | |
| "decoder_attention_heads": 20, | |
| "decoder_ffn_dim": 5120, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 32, | |
| "decoder_start_token_id": 50258, | |
| "dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "encoder_attention_heads": 20, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 32, | |
| "eos_token_id": 50257, | |
| "init_std": 0.02, | |
| "mask_feature_length": 10, | |
| "mask_feature_min_masks": 0, | |
| "mask_feature_prob": 0.0, | |
| "mask_time_length": 10, | |
| "mask_time_min_masks": 2, | |
| "mask_time_prob": 0.05, | |
| "max_length": 448, | |
| "max_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "median_filter_width": 7, | |
| "model_type": "whisper", | |
| "num_hidden_layers": 32, | |
| "num_mel_bins": 128, | |
| "scale_embedding": false, | |
| "use_cache": true, | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 51866 | |
| } | |
| } | |