HF Model & Benchmark Matrix

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

whisper-medium-uzbek

navai-uz/whisper-medium-uzbek

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-medium
provider
navai-uz
license
apache-2.0
language
uz
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
138
likes
1
created
—
last modified
2026-07-19T15:12:45+00:00 (2026)
huggingface
https://huggingface.co/navai-uz/whisper-medium-uzbek
tags
transformerssafetensorswhisperautomatic-speech-recognitionuzbekuzasrspeech-recognitionnavaidataset:mozilla-foundation/common_voice_22_0dataset:google/fleursdataset:k2speech/FeruzaSpeecharxiv:2107.14419arxiv:2205.12446base_model:openai/whisper-mediumbase_model:finetune:openai/whisper-mediumlicense:apache-2.0model-indexendpoints_compatibleregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WER FLEURSspeech-asr26.33low| [`whisper-tiny`](https://huggingface.co/navai-uz/whisper-tiny-uzbek) | 39M | 18.13 | 17.2 | 11.51 | 26.33 | 18.71 | 15.98 |
WER Common Voicespeech-asr22.0mediumCommon Voice 22.0

Discussions (0)

none scraped.

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