HF Model & Benchmark Matrix

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

whisper-small-cantonese

alvanlii/whisper-small-cantonese

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-small
provider
alvanlii
license
apache-2.0
language
zh, yue
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
181,556
likes
118
created
—
last modified
2025-11-20T04:10:40+00:00 (2025)
huggingface
https://huggingface.co/alvanlii/whisper-small-cantonese
tags
transformerspytorchsafetensorswhisperautomatic-speech-recognitionwhisper-eventgenerated_from_trainerzhyuedataset:mozilla-foundation/common_voice_16_0dataset:mozilla-foundation/common_voice_17_0arxiv:2201.02419base_model:openai/whisper-smallbase_model:finetune:openai/whisper-smalllicense:apache-2.0model-indexendpoints_compatibleregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr85.0Common Voice 16.0 yue Trainmedium| Common Voice 16.0 yue Train | 85 |
WER Common Voicespeech-asr16.0mediumCommon Voice 16.0

Discussions (0)

none scraped.

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