HF Model & Benchmark Matrix

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

whisper-large-v3-urdu

kingabzpro/whisper-large-v3-urdu

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-large-v3
provider
kingabzpro
license
apache-2.0
language
ur
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
486
likes
2
created
—
last modified
2025-07-11T16:06:29+00:00 (2025)
huggingface
https://huggingface.co/kingabzpro/whisper-large-v3-urdu
tags
transformerstensorboardsafetensorswhisperautomatic-speech-recognitionurdumozilla-foundation/common_voice_17_0hf-asr-leaderboardurdataset:mozilla-foundation/common_voice_17_0base_model:openai/whisper-large-v3base_model:finetune:openai/whisper-large-v3license:apache-2.0model-indexendpoints_compatibleregion:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr26.02**WER**medium| **WER** | 26.019% | Word Error Rate (lower is better) |
WERspeech-asr21.47mediumWer: 21.4712
WER Common Voicespeech-asr17.0mediumCommon Voice 17.0
CERspeech-asr9.43**CER**medium| **CER** | 9.426% | Character Error Rate |
CERspeech-asr7.2mediumCer: 7.1975

Discussions (0)

none scraped.

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