HF Model & Benchmark Matrix

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

whisper-small-malayalam

sajilck/whisper-small-malayalam

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-small
provider
sajilck
license
apache-2.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
228
likes
1
created
—
last modified
2026-07-18T05:14:00+00:00 (2026)
huggingface
https://huggingface.co/sajilck/whisper-small-malayalam
tags
safetensorswhisperautomatic-speech-recognitionmalayalamlow-resource-asrindic-languagesggmlwhisper-cppmldataset:sajilck/malayalam-asr-corpusbase_model:openai/whisper-smallbase_model:finetune:openai/whisper-smalllicense:apache-2.0region:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr70.7CommonVoicemedium| CommonVoice | 70.7% |
RTFspeech-asr40.0low| FP16 | [ggml-model-f16.bin](ggml/ggml-model-f16.bin) | 487 MB | 0.40 | 2.6× real-time | Best quality |
WERspeech-asr37.64mediumWER:** 37.64%
WER Common Voicespeech-asr25.0mediumCommonVoice 25

Discussions (0)

none scraped.

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