metricgan-plus-voicebank

speechbrain/metricgan-plus-voicebank

Audio to AudiospeechbrainLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
15.1K
Total downloads
650.8K
Gained 7D
+4,600(increase)
0.7%(up) vs baseline
Gained 30D
—
Likes
72
+0 in 7D
Rank · tracked models
#6,635
23(down 23 places)this week
Parameters
—
Last source update
Feb 28, 2024
Momentum
58.3
  • metricgan-plus-voicebank gained 4,600 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

metricgan-plus-voicebank is a audio to audio model published by speechbrain. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 4, 2026.

Published
Mar 2, 2022
Last updated
Feb 28, 2024
Library
speechbrain
License
apache-2.0
Task
Audio to Audio
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
657
speechbrainaudio-to-audiospeech-enhancementPyTorchendataset:Voicebankdataset:DEMANDarxiv:2104.03538arxiv:2106.04624license:apache-2.0region:us

Similar models

Models similar to metricgan-plus-voicebank
ModelDL 30D
bigvgan_v2_22khz_80band_256xnvidia1.3M
bigvgan_v2_44khz_128band_512xnvidia915.5K
MioCodec-25Hz-44.1kHz-v2Aratako528.8K
Qwen3-TTS-Tokenizer-12HzQwen305.5K
personaplex-7b-v1nvidia167.3K
TIGER-DnRJusperLee96.3K
speechbrain/metricgan-plus-voicebank — Downloads, Growth & Stats | OpenModelStats