Text-to-Speech
Transformers
Safetensors
English
moss_tts_delay
feature-extraction
tts
speech-synthesis
indian-english
indian-accent
voice-agent
voice-assistant
customer-support
conversational
moss-tts
lora
audio
custom_code
Eval Results (legacy)
Instructions to use IOTEverythin/roxi-tts-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IOTEverythin/roxi-tts-pro with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="IOTEverythin/roxi-tts-pro", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("IOTEverythin/roxi-tts-pro", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "additional_mlp_ffn_hidden_size": 2048, | |
| "architectures": [ | |
| "MossTTSDelayModel" | |
| ], | |
| "audio_assistant_delay_slot_token_id": 151662, | |
| "audio_assistant_gen_slot_token_id": 151656, | |
| "audio_end_token_id": 151653, | |
| "audio_pad_code": 1024, | |
| "audio_start_token_id": 151652, | |
| "audio_user_slot_token_id": 151654, | |
| "audio_vocab_size": 1024, | |
| "auto_map": { | |
| "AutoConfig": "configuration_moss_tts.MossTTSDelayConfig", | |
| "AutoModel": "modeling_moss_tts.MossTTSDelayModel" | |
| }, | |
| "dtype": "bfloat16", | |
| "hidden_size": 2048, | |
| "im_end_token_id": 151645, | |
| "im_start_token_id": 151644, | |
| "initializer_range": 0.02, | |
| "language_config": { | |
| "_name_or_path": "Qwen/Qwen3-8B", | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "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", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 151643, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 155648 | |
| }, | |
| "local_ffn_hidden_size": 8960, | |
| "local_hidden_size": 1536, | |
| "local_num_layers": 4, | |
| "model_type": "moss_tts_delay", | |
| "n_vq": 32, | |
| "pad_token_id": 151643, | |
| "sampling_rate": 24000, | |
| "transformers_version": "5.0.0", | |
| "vocab_size": 155648 | |
| } | |