HF Model & Benchmark Matrix

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

kazakh-whisper-large-v3-turbo

shyngys879/kazakh-whisper-large-v3-turbo

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-large-v3-turbo
provider
shyngys879
license
apache-2.0
language
kk
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
164,712
likes
11
created
—
last modified
2026-06-16T17:20:24+00:00 (2026)
huggingface
https://huggingface.co/shyngys879/kazakh-whisper-large-v3-turbo
tags
transformerssafetensorswhisperautomatic-speech-recognitionspeech-recognitionasrspeech-to-textwhisper-large-v3-turbokazakhkazakh-asrkazakh-languagekazakh-speechpytorchfleurssubtitlesvoice-assistantkkdataset:issai/Kazakh_Speech_Corpus_2dataset:farabi-lab/kazakh-sttdataset:voice-biomarkers/openslr-140-hq-Kazakhdataset:Flamme-VRM/kazakh-speech-datasetdataset:SRP-base-model-training/kazakh_speech_dataset_ksddataset:Shirali/ISSAI_KSC_335RS_v_1_1dataset:SRP-base-model-training/kazakh_speech_corpus_2

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr11.8low| **Kazakh Whisper Large-v3 Turbo** | **11.80%** | **4.98%** |
RTFspeech-asr6.46low| **Kazakh Whisper Large-v3 Turbo** | **11.80%** | **4.98%** | **117.28 sec** | **0.0646** | **15.48×** |
CERspeech-asr4.98low| **Kazakh Whisper Large-v3 Turbo** | **11.80%** | **4.98%** |

Discussions (0)

none scraped.

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