STT-Comparison / data /inference /benchmark_results.json
danielrosehill's picture
commit
b5a4032
{
"ground_truth_file": "/home/daniel/repos/github/Long-Form-Audio-Eval/data/ground-truth/truth_1.txt",
"total_runs_evaluated": 8,
"results": [
{
"run_id": "run-1",
"run_type": "local-stt",
"provider": "local",
"model": "whisper-base",
"engine": "Buzz",
"metrics": {
"wer": 17.52,
"cer": 5.38,
"word_accuracy": 82.48,
"insertions": 44,
"deletions": 62,
"substitutions": 726,
"hits": 3960
}
},
{
"run_id": "run-2",
"run_type": "local-stt",
"provider": "local",
"model": "whisper-tiny",
"engine": "Buzz",
"metrics": {
"wer": 22.49,
"cer": 8.39,
"word_accuracy": 77.51,
"insertions": 82,
"deletions": 155,
"substitutions": 831,
"hits": 3762
}
},
{
"run_id": "run-3",
"run_type": "local-stt",
"provider": "local",
"model": "whisper-base",
"engine": "Buzz",
"metrics": {
"wer": 17.52,
"cer": 5.38,
"word_accuracy": 82.48,
"insertions": 44,
"deletions": 62,
"substitutions": 726,
"hits": 3960
}
},
{
"run_id": "manual-1",
"run_type": "cloud-stt",
"provider": "gladia",
"model": "solaria-1",
"engine": "api",
"metrics": {
"wer": 20.83,
"cer": 6.3,
"word_accuracy": 79.17,
"insertions": 100,
"deletions": 92,
"substitutions": 797,
"hits": 3859
}
},
{
"run_id": "manual-2",
"run_type": "cloud-stt",
"provider": "deepgram",
"model": "nova-3",
"engine": "api",
"metrics": {
"wer": 18.72,
"cer": 7.33,
"word_accuracy": 81.28,
"insertions": 60,
"deletions": 214,
"substitutions": 615,
"hits": 3919
}
},
{
"run_id": "manual-3",
"run_type": "cloud-stt",
"provider": "assemblyai",
"model": "best",
"engine": "api",
"metrics": {
"wer": 18.79,
"cer": 6.24,
"word_accuracy": 81.21,
"insertions": 64,
"deletions": 156,
"substitutions": 672,
"hits": 3920
}
},
{
"run_id": "manual-4",
"run_type": "cloud-stt",
"provider": "speechmatics",
"model": "slam-1-global-english",
"engine": "api",
"metrics": {
"wer": 21.65,
"cer": 7.15,
"word_accuracy": 78.35,
"insertions": 158,
"deletions": 51,
"substitutions": 819,
"hits": 3878
}
},
{
"run_id": "manual-5",
"run_type": "cloud-stt",
"provider": "openai",
"model": "whisper-1",
"engine": "api",
"metrics": {
"wer": 19.27,
"cer": 6.4,
"word_accuracy": 80.73,
"insertions": 114,
"deletions": 106,
"substitutions": 695,
"hits": 3947
}
}
]
}