Model comparison
romanian-wav2vec2 vs Gemini 2.5 Pro
Capability radar, value bars, and side-by-side posture.
romanian-wav2vec2
Not scored
value score
Gemini 2.5 Pro
93
value score
romanian-wav2vec2 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 | romanian-wav2vec2 | Gemini 2.5 Pro |
|---|---|---|
| Developer | gigant (Théo Gigant) | 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 fine-tuned wav2vec2-xls-r-300m model for Romanian automatic speech recognition, converting 16 kHz audio into lowercased Romanian text without punctuation. Optionally paired with a 5-gram language model trained on Romanian parliamentary corpora for improved decoding accuracy. | Google frontier multimodal model. |