HF Model & Benchmark Matrix

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

whisper-large-v3-lv-late-cv19

AiLab-IMCS-UL/whisper-large-v3-lv-late-cv19

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
openai/whisper-large-v3
provider
AiLab-IMCS-UL
license
apache-2.0
language
lv
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
337
likes
10
created
—
last modified
2024-10-21T06:02:55+00:00 (2024)
huggingface
https://huggingface.co/AiLab-IMCS-UL/whisper-large-v3-lv-late-cv19
tags
safetensorswhisperautomatic-speech-recognitionlvbase_model:openai/whisper-large-v3base_model:finetune:openai/whisper-large-v3license:apache-2.0region:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr19.0mediumCommon Voice 19.0
WERspeech-asr4.8low| Latvian Common Voice 19.0 test set (VW) - formatted | 4.8 | 1.6 |
WER Common Voicespeech-asr4.8Latvian Common Voice 19.0 test set (VW) - formattedmedium| Latvian Common Voice 19.0 test set (VW) - formatted | 4.8 | 1.6 |
WER Common Voicespeech-asr3.2Latvian Common Voice 19.0 test set (VW) - normalizedmedium| Latvian Common Voice 19.0 test set (VW) - normalized | 3.2 | 1.0 |
CERspeech-asr1.6low| Latvian Common Voice 19.0 test set (VW) - formatted | 4.8 | 1.6 |

Discussions (0)

none scraped.

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