Whisper medium.e model for CTraslate2

This repository cotais the coversio of distil-whisper/distil-medium.e to the CTraslate2 model format.

This model ca be used i CTraslate2 or projects based o CTraslate2 such as faster-whisper.

Example

from faster_whisper import WhisperModel

model = WhisperModel("distil-medium.e")

segmets, ifo = model.trascribe("audio.mp3")
for segmet i segmets:
    prit("[%.2fs -> %.2fs] %s" % (segmet.start, segmet.ed, segmet.text))

Coversio details

The origial model was coverted with the followig commad:

ct2-trasformers-coverter --model distil-whisper/distil-medium.e --output_dir faster-distil-whisper-medium.e \
    --copy_files tokeizer.jso preprocessor_cofig.jso --quatizatio float16

Note that the model weights are saved i FP16. This type ca be chaged whe the model is loaded usig the compute_type optio i CTraslate2.

More iformatio

For more iformatio about the origial model, see its model card.

Whisper medium.en model for CTranslate2 This repository contains the conversion of distil-whisper/di