Model comparison
Conv-TasNet Libri1Mix (vokra) vs Gemini 2.5 Pro
Capability radar, value bars, and side-by-side posture.
Conv-TasNet Libri1Mix (vokra)
Not scored
value score
Gemini 2.5 Pro
93
value score
Conv-TasNet Libri1Mix (vokra) ctx
—
Gemini 2.5 Pro ctx
1.0M
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Gemini 2.5 Pro93
Attribute tape
| Field | Conv-TasNet Libri1Mix (vokra) | Gemini 2.5 Pro |
|---|---|---|
| Developer | Vokra | Google DeepMind |
| Context | — | 1.0M |
| Modalities | Text, Code, Image, Audio, Video | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $1.25/1M in · $10/1M out |
| Value score | — | 93 |
| Summary | A Conv-TasNet speech enhancement model trained on the Libri1Mix enh_single task at 16 kHz, capable of separating and cleaning speech from noisy single-channel audio mixtures entirely in the time domain. It is derived from the Asteroid librimix recipe and closely mirrors the JorisCos/ConvTasNet_Libri1Mix_enhsingle_16k reference artifact. | Google frontier multimodal model. |