This is the CTranslate2 version which is faster than base version.

requirements

pip install ctranslate2

Base model to Ctranslate format conversion

!ct2-transformers-converter --model sha1779/BengaliRegionalASR --output_dir sha1779/Faster_BengaliRegionalASR --copy_files tokenizer.json preprocessor_config.json --quantization float16

Run the model

pip install faster-whisper
from faster_whisper import WhisperModel

model_size = "sha1779/Faster_BengaliRegionalASR"

model = WhisperModel(model_size, device="cuda", compute_type="float16")
segments, info = model.transcribe("audio.mp3", beam_size=5, language="en", condition_on_previous_text=False)

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
Downloads last month
15
Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for sha1779/Faster_BengaliRegionalASR

Finetuned
(1)
this model