Automatic Speech Recognition
Transformers
Safetensors
PEFT
English
whisper
representation-editing
aura
myst
Instructions to use balaji1312/whisper-medium-myst-aura with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use balaji1312/whisper-medium-myst-aura with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="balaji1312/whisper-medium-myst-aura")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("balaji1312/whisper-medium-myst-aura") model = AutoModelForSpeechSeq2Seq.from_pretrained("balaji1312/whisper-medium-myst-aura", device_map="auto") - PEFT
How to use balaji1312/whisper-medium-myst-aura with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Download config.json from balaji1312/whisper-medium-myst-aura: direct link, hf CLI and curl.
- Browser
- Download file 2.83 kB
-
https://huggingface.co/balaji1312/whisper-medium-myst-aura/resolve/main/config.json
- Command line
-
hf download hf://balaji1312/whisper-medium-myst-aura/config.json
-
curl -L -o config.json https://huggingface.co/balaji1312/whisper-medium-myst-aura/resolve/main/config.json
2.83 kB
| { | |
| "_name_or_path": "openai/whisper-medium.en", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "apply_spec_augment": false, | |
| "architectures": [ | |
| "WhisperForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50256 | |
| ], | |
| "bos_token_id": 50257, | |
| "classifier_proj_size": 256, | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 24, | |
| "decoder_start_token_id": 50257, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 24, | |
| "eos_token_id": 50256, | |
| "forced_decoder_ids": null, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "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": null, | |
| "max_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "median_filter_width": 7, | |
| "model_type": "whisper", | |
| "num_hidden_layers": 24, | |
| "num_mel_bins": 80, | |
| "pad_token_id": 50256, | |
| "peft_config": { | |
| "bottleneck_dim": 32, | |
| "dropout": 0.1, | |
| "head_select_heads": [ | |
| 1, | |
| 6, | |
| 11 | |
| ], | |
| "head_select_layers": null, | |
| "head_select_target_modules": [ | |
| "self_attn" | |
| ], | |
| "head_select_train_bias": true, | |
| "jola_encoder_train": false, | |
| "jola_gate_hp": { | |
| "eps": 1e-06, | |
| "stretch_limits": [ | |
| -0.1, | |
| 1.1 | |
| ], | |
| "temperature": 1.0 | |
| }, | |
| "jola_gate_scheduler": "linear", | |
| "jola_gate_type": "dynamic", | |
| "jola_gate_type_per_target": null, | |
| "jola_sparsity_weight": 0.1, | |
| "jola_target_modules": [ | |
| "encoder_attn" | |
| ], | |
| "lofit_mode": "soft", | |
| "lofit_selected_heads": null, | |
| "lofit_target_modules": [ | |
| "encoder_attn" | |
| ], | |
| "lora_alpha": 256, | |
| "lora_dim": 128, | |
| "lora_full_encoder_ft": false, | |
| "lora_target_modules": null, | |
| "peft_decoder_layers": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 22, | |
| 23, | |
| 24 | |
| ], | |
| "peft_encoder_layers": [], | |
| "peft_type": "jola", | |
| "prefix_dropout_rate": 0.0, | |
| "prefix_hidden_dim": 16, | |
| "prefix_n_layer": 12, | |
| "prefix_seq_len": [ | |
| 50, | |
| 10 | |
| ], | |
| "prompt_init_vocab": true, | |
| "prompt_n_tokens": [ | |
| 100, | |
| 20 | |
| ], | |
| "prompt_random_range": 0.5, | |
| "reft_positions": null, | |
| "to_decoder": true, | |
| "to_encoder": false | |
| }, | |
| "pif_loss_alpha": 1.0, | |
| "scale_embedding": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.3", | |
| "use_cache": false, | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 51864 | |
| } | |