HF Model & Benchmark Matrix

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

thewhisper-large-v3-turbo

TheStageAI/thewhisper-large-v3-turbo

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-large-v3-turbo
provider
TheStageAI
license
cc-by-4.0
language
en, ar, bg, bn, cs, da, de, el, es, et, fi, fr
context
—
library
coreml
vRAM (GB)
—
size on disk
—
downloads
1,938
likes
26
created
—
last modified
2026-07-29T17:51:29+00:00 (2026)
huggingface
https://huggingface.co/TheStageAI/thewhisper-large-v3-turbo
tags
coremlonnxsafetensorswhisperautomatic-speech-recognitionaudiospeechmultilingualstreamingcudanvidiaapple-siliconon-deviceiosmacosenarbgbncsdadeeles

Benchmark scores (19)

benchmarkcategoryscorecontextconfevidence
WER Earnings-22speech-asr11.57**Earnings-22**medium| **Earnings-22** | 11.57 | 11.15 | 11.09 | 11.21 | 10.89 |
WER AMIspeech-asr9.6**AMI**medium| **AMI** | 9.6 | 9.35 | 9.38 | 9.14 | 9.2 |
WER GigaSpeechspeech-asr9.56**GigaSpeech**medium| **GigaSpeech** | 9.56 | 9.54 | 9.53 | 9.48 | 9.51 |
WER VoxPopulispeech-asr7.37**VoxPopuli**medium| **VoxPopuli** | 7.37 | 6.36 | 6.34 | 6.71 | 6.28 |
WER MLSspeech-asr6.89**MLS Italian**medium| **MLS Italian** | 6.89 | 7.01 | 7.11 | 7.36 | 6.12 |
WERspeech-asr6.12**Mean WER**medium| **Mean WER** | 6.12 | 5.9 | 5.88 | 5.89 | 5.8 |
WER MLSspeech-asr5.69**MLS Portuguese**medium| **MLS Portuguese** | 5.69 | 5.53 | 5.34 | 6.3 | 4.56 |
WER FLEURSspeech-asr5.18**FLEURS FR**medium| **FLEURS FR** | 5.18 | 5.15 | 5.27 | 5.25 | 4.99 |
WER FLEURSspeech-asr4.81**FLEURS PT**medium| **FLEURS PT** | 4.81 | 4.78 | 4.7 | 4.7 | 4.55 |
WER MLSspeech-asr4.67**MLS French**medium| **MLS French** | 4.67 | 4.54 | 4.48 | 4.31 | 3.77 |
WER FLEURSspeech-asr4.62**FLEURS DE**medium| **FLEURS DE** | 4.62 | 4.66 | 4.66 | 4.5 | 4.36 |
WER MLSspeech-asr4.28**MLS German**medium| **MLS German** | 4.28 | 4.16 | 4.19 | 4.12 | 3.77 |
WER LibriSpeechspeech-asr3.77**LibriSpeech Other**medium| **LibriSpeech Other** | 3.77 | 3.76 | 3.75 | 3.72 | 3.63 |
WER TED-LIUMspeech-asr3.37**TED-LIUM**medium| **TED-LIUM** | 3.37 | 3.3 | 3.29 | 3.25 | 3.33 |
WER FLEURSspeech-asr3.25**FLEURS ES**medium| **FLEURS ES** | 3.25 | 3.16 | 3.15 | 3.04 | 2.98 |
WER FLEURSspeech-asr3.21**FLEURS IT**medium| **FLEURS IT** | 3.21 | 3.26 | 3.43 | 3.45 | 2.82 |
WER MLSspeech-asr2.93**MLS Spanish**medium| **MLS Spanish** | 2.93 | 2.84 | 2.71 | 2.85 | 2.51 |
WER SPGISpeechspeech-asr1.92**SPGISpeech**medium| **SPGISpeech** | 1.92 | 1.93 | 1.92 | 1.88 | 1.88 |
WER LibriSpeechspeech-asr1.83**LibriSpeech Clean**medium| **LibriSpeech Clean** | 1.83 | 1.8 | 1.74 | 1.73 | 1.71 |

Discussions (0)

none scraped.

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