| { | |
| "module": "keras_hub.src.models.whisper.whisper_tokenizer", | |
| "class_name": "WhisperTokenizer", | |
| "config": { | |
| "name": "whisper_tokenizer", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "int32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "config_file": "tokenizer.json", | |
| "sequence_length": null, | |
| "add_prefix_space": false, | |
| "unsplittable_tokens": [ | |
| "<|startoftranscript|>", | |
| "<|endoftext|>", | |
| "<|notimestamps|>", | |
| "<|translate|>", | |
| "<|transcribe|>" | |
| ], | |
| "special_tokens": { | |
| "<|startoftranscript|>": 50257, | |
| "<|endoftext|>": 50256, | |
| "<|notimestamps|>": 50362, | |
| "<|translate|>": 50358, | |
| "<|transcribe|>": 50357 | |
| }, | |
| "language_tokens": null | |
| }, | |
| "registered_name": "keras_hub>WhisperTokenizer" | |
| } |