HF Model & Benchmark Matrix

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

whisper-th-medium-timestamp

biodatlab/whisper-th-medium-timestamp

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
biodatlab/whisper-th-medium-combined
provider
biodatlab
license
mit
language
th
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
194
likes
3
created
—
last modified
2024-09-12T09:03:04+00:00 (2024)
huggingface
https://huggingface.co/biodatlab/whisper-th-medium-timestamp
tags
transformerssafetensorswhisperautomatic-speech-recognitionwhisper-eventgenerated_from_trainerthdataset:CMKL/Porjai-Thai-voice-dataset-centralbase_model:biodatlab/whisper-th-medium-combinedbase_model:finetune:biodatlab/whisper-th-medium-combinedlicense:mitmodel-indexendpoints_compatibleregion:usdeploy:azure

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr15.57mediumWER: 15.57
WER Common Voicespeech-asr13.0mediumCommon Voice 13

Discussions (0)

none scraped.

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