git lfs install
git clone https://huggingface.co/kurianbenoy/vegam-whisper-medium-ml-fp16

from faster_whisper import WhisperModel

model_path = "vegam-whisper-medium-ml-fp16"

# Run on GPU with FP16
model = WhisperModel(model_path, device="cuda", compute_type="float16")

segments, info = model.transcribe("audio.mp3", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

from faster_whisper import WhisperModel

model_path = "vegam-whisper-medium-ml-fp16"

model = WhisperModel(model_path, device="cuda", compute_type="float16")


segments, info = model.transcribe("00b38e80-80b8-4f70-babf-566e848879fc.webm", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

ct2-transformers-converter --model thennal/whisper-medium-ml --output_dir vegam-whisper-medium-ml-fp16 \
--quantization float16