HF Model & Benchmark Matrix

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

uz-whisper-small-stt-v2

maqsudxo1ja/uz-whisper-small-stt-v2

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
maqsudxo1ja/uz-whisper-small-stt
provider
maqsudxo1ja
license
apache-2.0
language
uz
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
191
likes
3
created
—
last modified
2026-07-18T04:10:52+00:00 (2026)
huggingface
https://huggingface.co/maqsudxo1ja/uz-whisper-small-stt-v2
tags
transformerssafetensorswhisperautomatic-speech-recognitionspeech-recognitionuzbeksttasrgenerated_from_traineruzdataset:islomov/it_youtube_uzbek_speech_datasetbase_model:maqsudxo1ja/uz-whisper-small-sttbase_model:finetune:maqsudxo1ja/uz-whisper-small-sttlicense:apache-2.0model-indexendpoints_compatibleregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr32.49low| 3.0847 | 0.68 | 400 | 0.3161 | 32.49 |
WERspeech-asr28.64**WER (Word Error Rate)**medium| **WER (Word Error Rate)** | **28.64%** |

Discussions (0)

none scraped.

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