Text-to-Speech
Transformers
Safetensors
audiodit
feature-extraction
audio
tts
environmental-tts
flow-matching
dit
custom_code
Instructions to use humanify/LongCat-AudioDiT-Env-TTS-1B-augment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use humanify/LongCat-AudioDiT-Env-TTS-1B-augment with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="humanify/LongCat-AudioDiT-Env-TTS-1B-augment", trust_remote_code=True, device_map="auto")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("humanify/LongCat-AudioDiT-Env-TTS-1B-augment", trust_remote_code=True, dtype="auto", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "AudioDiTModel" | |
| ], | |
| "dit_adaln_type": "global", | |
| "dit_adaln_use_text_cond": true, | |
| "dit_bias": true, | |
| "dit_cross_attn": true, | |
| "dit_cross_attn_norm": false, | |
| "dit_depth": 24, | |
| "dit_dim": 1536, | |
| "dit_dropout": 0.0, | |
| "dit_eps": 1e-06, | |
| "dit_ff_mult": 4, | |
| "dit_heads": 24, | |
| "dit_long_skip": true, | |
| "dit_qk_norm": true, | |
| "dit_text_conv": true, | |
| "dit_text_dim": 768, | |
| "dit_use_latent_condition": true, | |
| "dtype": "float32", | |
| "latent_dim": 64, | |
| "latent_hop": 2048, | |
| "max_wav_duration": 30, | |
| "model_type": "audiodit", | |
| "repa_dit_layer": 8, | |
| "sampling_rate": 24000, | |
| "sigma": 0.0, | |
| "text_add_embed": true, | |
| "text_encoder_config": { | |
| "_name_or_path": "ArthurZ/umt5-base", | |
| "architectures": [ | |
| "UMT5ForConditionalGeneration" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "dtype": "float32", | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "umt5", | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "scalable_attention": true, | |
| "use_cache": true, | |
| "vocab_size": 256384 | |
| }, | |
| "text_encoder_model": "google/umt5-base", | |
| "text_norm_feat": true, | |
| "transformers_version": "4.57.6", | |
| "vae_config": { | |
| "c_mults": [ | |
| 1, | |
| 2, | |
| 4, | |
| 8, | |
| 16 | |
| ], | |
| "channels": 128, | |
| "downsample_shortcut": "averaging", | |
| "downsampling_ratio": 2048, | |
| "dtype": "float32", | |
| "encoder_latent_dim": 128, | |
| "final_tanh": false, | |
| "in_channels": 1, | |
| "in_shortcut": "duplicating", | |
| "latent_dim": 64, | |
| "model_type": "audiodit_vae", | |
| "out_shortcut": "averaging", | |
| "sample_rate": 24000, | |
| "scale": 0.71, | |
| "strides": [ | |
| 2, | |
| 4, | |
| 4, | |
| 8, | |
| 8 | |
| ], | |
| "upsample_shortcut": "duplicating", | |
| "use_snake": true | |
| }, | |
| "auto_map": { | |
| "AutoConfig": "configuration_audiodit.AudioDiTConfig", | |
| "AutoModel": "modeling_audiodit.AudioDiTModel" | |
| } | |
| } |