Instructions to use vinai/PhoWhisper-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vinai/PhoWhisper-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="vinai/PhoWhisper-medium")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("vinai/PhoWhisper-medium") model = AutoModelForSpeechSeq2Seq.from_pretrained("vinai/PhoWhisper-medium", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from vinai/PhoWhisper-medium: direct link, hf CLI and curl.
- Browser
- Download file 1.33 kB
-
https://huggingface.co/vinai/PhoWhisper-medium/resolve/main/config.json
- Command line
-
hf download hf://vinai/PhoWhisper-medium/config.json
-
curl -L -o config.json https://huggingface.co/vinai/PhoWhisper-medium/resolve/main/config.json
1.33 kB
| { | |
| "_name_or_path": "./finetuned_models_FINAL/whisper-medium-vi/checkpoint-12000", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "apply_spec_augment": false, | |
| "architectures": [ | |
| "WhisperForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50257 | |
| ], | |
| "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": 50258, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 24, | |
| "eos_token_id": 50257, | |
| "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": 448, | |
| "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": 50257, | |
| "scale_embedding": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.31.0", | |
| "use_cache": true, | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 51865 | |
| } | |