HF Model & Benchmark Matrix

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

mtl-mimic-voicebank

speechbrain/mtl-mimic-voicebank

kind
original
quant
bf16 (16-bit)
family
misc
modality
audio-to-audio
root model
—
provider
speechbrain
license
apache-2.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
578
likes
35
created
—
last modified
2024-02-19T13:29:53+00:00 (2024)
huggingface
https://huggingface.co/speechbrain/mtl-mimic-voicebank
tags
speechbrainRobust ASRaudio-to-audiospeech-enhancementPyTorchendataset:Voicebankdataset:DEMANDarxiv:2106.04624license:apache-2.0region:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr2.89low| 22-06-21 | 3.05 | 3.74 | 2.89 | 2.80 |

Discussions (0)

none scraped.

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