Chih-Chiang Chang

Allow loading model from memory

5

Ctranslate2 supports this via the `files` argument (e.g. from result of requests)(https://opennmt.net/CTranslate2/python/ctranslate2.models.Whisper.html#ctranslate2.models.Whisper.__init__): ``` files – Load model files from the memory. This argument is a dictionary mapping file names to...

According to Figure 1 in the whisper paper, during training, the previous text tokens does not contain timestamp tokens. However, using trascribe with `without_timestamps=False` and `condition_on_previous_text=True`, the prompt tokens (which...

In `concatenate_dataset()`: https://github.com/huggingface/distil-whisper/blob/66ac8dd94963d08c28b868d6e1eeb328aab57c8b/training/run_pseudo_labelling.py#L644-L671 From my understanding, the logic in the for loop is - If either: 1. Adding the current utterance to `audio_sample` exceeds 30s 2. The current `speaker` is...