HF Model & Benchmark Matrix

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

whisper-podlodka-turbo

bond005/whisper-podlodka-turbo

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-large-v3-turbo
provider
bond005
license
apache-2.0
language
en, ru
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
1,176
likes
42
created
—
last modified
2026-01-29T10:12:53+00:00 (2026)
huggingface
https://huggingface.co/bond005/whisper-podlodka-turbo
tags
transformerssafetensorswhisperautomatic-speech-recognitionenrudataset:mozilla-foundation/common_voice_17_0dataset:bond005/rulibrispeechdataset:bond005/podlodka_speechdataset:bond005/sberdevices_golos_10h_crowddataset:bond005/sberdevices_golos_100h_farfielddataset:bond005/taiga_speech_v2dataset:bond005/audioset-nonspeecharxiv:2212.04356base_model:openai/whisper-large-v3-turbobase_model:finetune:openai/whisper-large-v3-turbolicense:apache-2.0model-indexendpoints_compatibleregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr11.0mediumCommon Voice 11
WER LibriSpeechspeech-asr9.76rulibrispeechmedium| rulibrispeech | 9.76 | 10.25 |
WER Common Voicespeech-asr5.22common_voice_11_0medium| common_voice_11_0 | 5.22 | 6.63 |

Discussions (0)

none scraped.

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