mel-roformer-kim-vocal-2-mlx
mlx-community/mel-roformer-kim-vocal-2-mlx
Tracked by OpenModelStats since August 25, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 180
- Total downloadsCumulative all-time download counter reported by the source platform.
- 839
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +14(increase)
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 10
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #80 among tracked Audio to Audio models.
- #57,001
- 396(down 396 places)this week
- Parameters
- 228M
- Last source update
- May 1, 2026
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 12.6
- mel-roformer-kim-vocal-2-mlx gained 14 downloads during the last seven tracked days.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
mel-roformer-kim-vocal-2-mlx is a audio to audio model published by mlx-community. OpenModelStats has tracked the model since Aug 25, 2026, most recently observing it Sep 17, 2026.
- Published
- Apr 25, 2026
- Last updated
- May 1, 2026
- Library
- mlx
- License
- mit
- Task
- Audio to Audio
- Parameters
- 228,203,172
- Spaces
- 0
- Derivative models
- —
- Velocity 7D/day
- 2
mlxsafetensorsmel_band_roformeraudioaudio-to-audiosource-separationmusic-source-separationvocal-separationmel-band-roformerroformerapple-siliconarxiv:2310.01809
Publisher
mlx-communityView publisher statistics →Derived from KimberleyJSN/melbandroformer (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| focalcodec_50hz_4k_causallucadellalib | 669 |
| Humaneness-Voice-Converterlaion | 0 |
| Qwen3-TTS-Tokenizer-12Hz-48kHztakuma104 | 865 |
| Qwen3-TTS-Tokenizer-12HzQwen | 211.7K |
| Ace-Step-1.5-ScragVAEscragnog | 5,014 |
| KVAE-Audiokandinskylab | 187 |