HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

kotoba-whisper-v2.0

kotoba-tech/kotoba-whisper-v2.0

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
kotoba-tech/kotoba-whisper-v2.0
provider
kotoba-tech
license
apache-2.0
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
11,473
likes
95
created
—
last modified
2024-10-23T00:47:28+00:00 (2024)
huggingface
https://huggingface.co/kotoba-tech/kotoba-whisper-v2.0
tags
transformerssafetensorswhisperautomatic-speech-recognitionaudiohf-asr-leaderboardjadataset:japanese-asr/whisper_transcriptions.reazonspeech.alldataset:japanese-asr/whisper_transcriptions.reazonspeech.all.wer_10.0dataset:japanese-asr/whisper_transcriptions.reazonspeech.all.wer_10.0.vectorizedarxiv:2212.04356arxiv:2311.00430license:apache-2.0model-indexendpoints_compatibleregion:usdeploy:azure

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr8.0mediumCommonVoice 8.0

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.