HF Model & Benchmark Matrix

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

whisper-large-v3-turbo-cantonese-yue-english

JackyHoCL/whisper-large-v3-turbo-cantonese-yue-english

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-large-v3-turbo
provider
JackyHoCL
license
mit
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
350
likes
13
created
—
last modified
2025-10-11T08:36:14+00:00 (2025)
huggingface
https://huggingface.co/JackyHoCL/whisper-large-v3-turbo-cantonese-yue-english
tags
transformerssafetensorswhisperautomatic-speech-recognitiondataset:mozilla-foundation/common_voice_17_0dataset:mozilla-foundation/common_voice_16_1dataset:JackyHoCL/cleaned_mixed_cantonese_and_english_speechbase_model:openai/whisper-large-v3-turbobase_model:finetune:openai/whisper-large-v3-turbolicense:mitendpoints_compatibleregion:usdeploy:azure

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr64.0mozilla-foundation/common_voice_17_0medium| mozilla-foundation/common_voice_17_0 | yue | test | **0.64** |
CERspeech-asr13.7mediumCER: 13.7%
WER Common Voicespeech-asr11.89mozilla-foundation/common_voice_16_1medium| mozilla-foundation/common_voice_16_1 | zh-CN | test | 11.89 |

Discussions (0)

none scraped.

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