Downloads · 30 days
37
12% of all-time downloads
language-and-voice-lab/whisper-large-icelandic-30k-steps-1000h-ct2
whisper-large-icelandic-30k-steps-1000h-ct2 is a automatic speech recognition model from language-and-voice-lab. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-4.0.
This is a faster-whisper version of language-and-voice-lab/whisper-large-icelandic-30k-steps-1000h.
Downloads · 30 days
37
12% of all-time downloads
All-time downloads
315
Public
Repo size
3.1 GB
Likes
0
Public
Click a slice to open those files.
.bin3.1 GB · 100%
From the Hugging Face model README
This is a faster-whisper version of language-and-voice-lab/whisper-large-icelandic-30k-steps-1000h.
The model was created like described in faster-whisper:
ct2-transformers-converter --model language-and-voice-lab/whisper-large-icelandic-30k-steps-1000h \
--output_dir whisper-large-icelandic-30k-steps-1000h-ct2 \
--quantization float16
from faster_whisper import WhisperModel
model_size = "whisper-large-icelandic-30k-steps-1000h-ct2"
# Run on GPU with FP16
model = WhisperModel(model_size, device="cuda", compute_type="float16")
# or run on GPU with INT8
# model = WhisperModel(model_size, device="cuda", compute_type="int8_float16")
# or run on CPU with INT8
# model = WhisperModel(model_size, device="cpu", compute_type="int8")
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))
When publishing results based on these models please refer to:
@misc{gunnarsson2023whisperlarge30kicelandicct2,
title={Acoustic Model in Icelandic: whisper-large-icelandic-30k-steps-1000h-ct2.},
author={Gunnarsson, Thorsteinn Dadi and Hernandez Mena, Carlos Daniel},
url={https://huggingface.co/language-and-voice-lab/whisper-large-icelandic-30k-steps-1000h-ct2},
year={2023}
}