# Endpointing Model Benchmark Report

**Model:** `/data/smart-turn-v3.1-gpu.onnx`

**Generated:** 2025-12-03 16:21:25 UTC

## Accuracy Results

**Total Samples:** 31,473

**Unique Languages:** 🇸🇦 Arabic, 🇧🇩 Bengali, 🇩🇰 Danish, 🇩🇪 German, 🇬🇧 🇺🇸 English, 🇫🇮 Finnish, 🇫🇷 French, 🇮🇳 Hindi, 🇮🇩 Indonesian, 🇮🇹 Italian, 🇯🇵 Japanese, 🇰🇷 Korean, 🇮🇳 Marathi, 🇳🇱 Dutch, 🇳🇴 Norwegian, 🇵🇱 Polish, 🇵🇹 Portuguese, 🇷🇺 Russian, 🇪🇸 Spanish, 🇹🇷 Turkish, 🇺🇦 Ukrainian, 🇻🇳 Vietnamese, 🇨🇳 Chinese

**Unique Datasets:** chirp3_1, chirp3_2, human_5, human_convcollector_1, liva_1, midcentury_1, mundo_1, orpheus_endfiller_1, orpheus_grammar_1, orpheus_midfiller_1, rime_2

### Overall Performance
| Metric | Sample Count | Accuracy (%) | False Positives (%) | False Negatives (%) |
|--------|--------------|--------------|---------------------|---------------------|
| Overall | 31,473 | 93.98 | 3.21 | 2.81 |

### Performance by Language
| Language | Sample Count | Accuracy (%) | False Positives (%) | False Negatives (%) |
|----------|--------------|--------------|---------------------|---------------------|
| 🇯🇵 Japanese | 834 | 98.08 | 0.84 | 1.08 |
| 🇰🇷 Korean | 890 | 97.98 | 0.79 | 1.24 |
| 🇹🇷 Turkish | 966 | 97.52 | 1.24 | 1.24 |
| 🇳🇱 Dutch | 1,401 | 96.79 | 1.57 | 1.64 |
| 🇩🇪 German | 1,322 | 96.37 | 2.42 | 1.21 |
| 🇫🇷 French | 1,253 | 96.09 | 1.68 | 2.23 |
| 🇵🇹 Portuguese | 1,398 | 95.99 | 2.15 | 1.86 |
| 🇫🇮 Finnish | 1,010 | 95.74 | 2.18 | 2.08 |
| 🇵🇱 Polish | 976 | 95.59 | 2.56 | 1.84 |
| 🇮🇩 Indonesian | 971 | 95.57 | 2.47 | 1.96 |
| 🇬🇧 🇺🇸 English | 7,722 | 95.55 | 2.55 | 1.90 |
| 🇮🇹 Italian | 782 | 95.52 | 2.81 | 1.66 |
| 🇷🇺 Russian | 1,470 | 94.15 | 2.93 | 2.93 |
| 🇩🇰 Danish | 779 | 94.09 | 3.34 | 2.57 |
| 🇺🇦 Ukrainian | 929 | 93.97 | 2.58 | 3.44 |
| 🇳🇴 Norwegian | 1,014 | 93.69 | 3.25 | 3.06 |
| 🇮🇳 Hindi | 1,295 | 93.36 | 3.17 | 3.47 |
| 🇪🇸 Spanish | 1,791 | 90.95 | 5.75 | 3.29 |
| 🇨🇳 Chinese | 945 | 88.99 | 4.34 | 6.67 |
| 🇸🇦 Arabic | 947 | 88.91 | 6.44 | 4.65 |
| 🇮🇳 Marathi | 774 | 88.24 | 6.20 | 5.56 |
| 🇧🇩 Bengali | 1,000 | 85.10 | 7.10 | 7.80 |
| 🇻🇳 Vietnamese | 1,004 | 81.87 | 9.86 | 8.27 |

### Performance by Dataset
| Dataset | Sample Count | Accuracy (%) | False Positives (%) | False Negatives (%) |
|---------|--------------|--------------|---------------------|---------------------|
| midcentury_1 | 1,044 | 99.52 | 0.10 | 0.38 |
| human_5 | 402 | 98.51 | 0.50 | 1.00 |
| orpheus_endfiller_1 | 182 | 98.35 | 0.00 | 1.65 |
| rime_2 | 396 | 97.98 | 0.25 | 1.77 |
| liva_1 | 3,832 | 95.12 | 2.97 | 1.91 |
| chirp3_1 | 16,300 | 95.10 | 2.58 | 2.32 |
| orpheus_grammar_1 | 163 | 93.87 | 4.29 | 1.84 |
| chirp3_2 | 8,428 | 90.76 | 4.84 | 4.40 |
| human_convcollector_1 | 90 | 88.89 | 6.67 | 4.44 |
| orpheus_midfiller_1 | 140 | 87.86 | 5.00 | 7.14 |
| mundo_1 | 496 | 85.69 | 8.87 | 5.44 |