sepformer-wsj02mix
speechbrain/sepformer-wsj02mix
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 5,161
- Total downloadsCumulative all-time download counter reported by the source platform.
- 288.2K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +1,443(increase)
- 0.5%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 79
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #19 among tracked Audio to Audio models.
- #11,146
- 6(down 6 places)this week
- Parameters
- —
- Last source update
- Feb 19, 2024
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 53.2
- sepformer-wsj02mix gained 1,443 downloads during the last seven tracked days.
- It moved from #18 to #19 among tracked Audio to Audio models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
sepformer-wsj02mix is a audio to audio model published by speechbrain. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 4h ago.
- Published
- Mar 2, 2022
- Last updated
- Feb 19, 2024
- Library
- speechbrain
- License
- apache-2.0
- Task
- Audio to Audio
- Parameters
- —
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 206
speechbrainSource SeparationSpeech SeparationAudio Source SeparationWSJ02MixSepFormerTransformeraudio-to-audioaudio-source-separationendataset:WSJ0-2Mixarxiv:2010.13154
Similar models
| Model | DL 30D |
|---|---|
| bigvgan_v2_22khz_80band_256xnvidia | 1.3M |
| bigvgan_v2_44khz_128band_512xnvidia | 897.4K |
| MioCodec-25Hz-44.1kHz-v2Aratako | 570.6K |
| Qwen3-TTS-Tokenizer-12HzQwen | 223.6K |
| personaplex-7b-v1nvidia | 183.7K |
| TIGER-DnRJusperLee | 80.3K |