{% extends "base.html" %} {% block title %}Speech-to-text · {{ profile.name }}{% endblock %} {% block content %}
Benchmarks an STT model's real-time-factor (Lemonade's whispercpp/moonshine recipes,
a multipart /v1/audio/transcriptions). Deliberately separate from the model/router
leaderboard -- real-time-factor isn't comparable to LLM token throughput. This runs synchronously.
Couldn't reach this instance ({{ capabilities.error }}) -- engine and backend fall back to free text.
{% endif %}No STT results yet.
{% else %}| Timestamp | Model | Transcription (ms) | Audio (s) | RTF | Language | Valid | Notes |
|---|---|---|---|---|---|---|---|
| {{ r.timestamp }} | {{ r.model.name }} | {{ "%.1f"|format(r.metrics.transcription_time_ms) }} | {{ "%.2f"|format(r.metrics.audio_duration_s) }} | {{ "%.2f"|format(r.metrics.real_time_factor) }}x | {{ r.metrics.language or "–" }} | {{ "valid" if r.validity.valid else "invalid" }} | {{ r.validity.notes or "" }} |