HF Model & Benchmark Matrix

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

wav2vec2-bert-CV16-en

hf-audio/wav2vec2-bert-CV16-en

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
ylacombe/w2v-bert-2.0
provider
hf-audio
license
—
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
1,026
likes
8
created
—
last modified
2024-01-15T11:41:00+00:00 (2024)
huggingface
https://huggingface.co/hf-audio/wav2vec2-bert-CV16-en
tags
transformerstensorboardsafetensorswav2vec2-bertautomatic-speech-recognitionmozilla-foundation/common_voice_16_0generated_from_trainerenbase_model:ylacombe/w2v-bert-2.0base_model:finetune:ylacombe/w2v-bert-2.0endpoints_compatibleregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr14.55mediumWer: 0.1455
CERspeech-asr5.8mediumCer: 0.0580

Discussions (0)

none scraped.

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