Instructions to use amalia-llm/AMALIA-speech-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amalia-llm/AMALIA-speech-encoder with Transformers:
# Load model directly from transformers import AutoProcessor, WhisperEncoder processor = AutoProcessor.from_pretrained("amalia-llm/AMALIA-speech-encoder") model = WhisperEncoder.from_pretrained("amalia-llm/AMALIA-speech-encoder") - Notebooks
- Google Colab
- Kaggle
| { | |
| "transformers_version": "5.12.1", | |
| "architectures": [ | |
| "WhisperEncoder" | |
| ], | |
| "output_hidden_states": false, | |
| "return_dict": true, | |
| "dtype": "float32", | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": true, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "problem_type": null, | |
| "vocab_size": 51866, | |
| "num_mel_bins": 128, | |
| "encoder_layers": 32, | |
| "encoder_attention_heads": 20, | |
| "decoder_layers": 32, | |
| "decoder_attention_heads": 20, | |
| "decoder_ffn_dim": 5120, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layerdrop": 0.0, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_start_token_id": 50258, | |
| "use_cache": true, | |
| "activation_function": "gelu", | |
| "d_model": 1280, | |
| "dropout": 0.0, | |
| "attention_dropout": 0.0, | |
| "activation_dropout": 0.0, | |
| "init_std": 0.02, | |
| "scale_embedding": false, | |
| "max_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "pad_token_id": 50256, | |
| "bos_token_id": 50257, | |
| "eos_token_id": 50257, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "use_weighted_layer_sum": false, | |
| "classifier_proj_size": 256, | |
| "apply_spec_augment": false, | |
| "mask_time_prob": 0.05, | |
| "mask_time_length": 10, | |
| "mask_time_min_masks": 2, | |
| "mask_feature_prob": 0.0, | |
| "mask_feature_length": 10, | |
| "mask_feature_min_masks": 0, | |
| "median_filter_width": 7, | |
| "tie_word_embeddings": true, | |
| "_name_or_path": "inesc-id/WhisperLv3-FT-EP-CPP", | |
| "model_type": "whisper", | |
| "output_attentions": false, | |
| "source_model": "inesc-id/WhisperLv3-FT-EP-CPP", | |
| "base_processor": "openai/whisper-large-v3", | |
| "encoder_only": true | |
| } |