Automatic Speech Recognition
Transformers
Safetensors
voxtral
image-feature-extraction
speech
speech-language-model
target-speaker-asr
multi-talker
speaker-diarization
meeting-transcription
Dixtral
Voxtral
DiCoW
BUT-FIT
custom_code
Instructions to use BUT-FIT/Dixtral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BUT-FIT/Dixtral with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="BUT-FIT/Dixtral", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("BUT-FIT/Dixtral", trust_remote_code=True) model = AutoModel.from_pretrained("BUT-FIT/Dixtral", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "DixtralForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "additional_layer": false, | |
| "additional_self_attention_layer": false, | |
| "apply_fddt_to_n_layers": -1, | |
| "architectures": [ | |
| "DiCoWForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 50257, | |
| "ctc_loss_reduction": "mean", | |
| "ctc_weight": 0.0, | |
| "decoder_start_token_id": 50258, | |
| "dropout": 0.0, | |
| "eos_token_id": 50257, | |
| "fddt_bias_only": false, | |
| "fddt_init": "suppressive", | |
| "fddt_is_diagonal": true, | |
| "fddt_use_non_target": true, | |
| "fddt_use_overlap": true, | |
| "fddt_use_silence": true, | |
| "fddt_use_target": true, | |
| "final_dropout": 0.0, | |
| "head_dim": 64, | |
| "hidden_size": 1280, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "is_encoder_decoder": true, | |
| "layerdrop": 0.0, | |
| "max_length": null, | |
| "max_source_positions": 1500, | |
| "model_type": "voxtral_encoder", | |
| "non_target_fddt_value": 0.5, | |
| "num_attention_heads": 20, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 20, | |
| "num_mel_bins": 128, | |
| "pad_token_id": 50256, | |
| "pre_ctc_sub_sample": false, | |
| "remove_timestamps_from_ctc": true, | |
| "scale_embedding": false, | |
| "scb_layers": null, | |
| "torch_dtype": "float32", | |
| "use_dicow_encoder": true, | |
| "use_enrollments": false, | |
| "use_fddt": true, | |
| "use_pre_pos_fddt": true, | |
| "vocab_size": 51866 | |
| }, | |
| "audio_token_id": 24, | |
| "auto_map": { | |
| "AutoConfig": "configuration_dixtral.DixtralConfig", | |
| "AutoModel": "modeling_dixtral.DixtralForConditionalGeneration" | |
| }, | |
| "forced_decoder_ids": null, | |
| "hidden_size": 3072, | |
| "model_type": "voxtral", | |
| "num_soft_prompts": 0, | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 100000000.0, | |
| "sliding_window": null, | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.0", | |
| "vocab_size": 131072 | |
| } | |