HF Model & Benchmark Matrix

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

whisper-medium-et

TalTechNLP/whisper-medium-et

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
—
provider
TalTechNLP
license
cc-by-4.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
136
likes
2
created
—
last modified
2023-03-23T07:26:49+00:00 (2023)
huggingface
https://huggingface.co/TalTechNLP/whisper-medium-et
tags
transformerspytorchwhisperautomatic-speech-recognitionaudiohf-asr-leaderboardetlicense:cc-by-4.0model-indexendpoints_compatibleregion:usdeploy:azure

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr14.7Common Voice 11.0medium| Common Voice 11.0 | 14.7 |
WERspeech-asr13.8low| Common Voice 8.0 | 13.8 |
WER Common Voicespeech-asr13.8Common Voice 8.0medium| Common Voice 8.0 | 13.8 |
WER Common Voicespeech-asr8.0mediumCommon Voice 8.0

Discussions (0)

none scraped.

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