saturate
Batch inference for datasets: rows in, any OpenAI-compatible endpoint, resumable parquet out. Congestion-aware concurrency — no tuning.
- 56
- Python
- Apache-2.0
- 7 h ago
Batch inference for datasets: rows in, any OpenAI-compatible endpoint, resumable parquet out. Congestion-aware concurrency — no tuning.
Production-ready batch inference for Cohere’s Arabic/English ASR model, with optimized Silero VAD, multi-file GPU batching, subtitles, and optional word-level timestamps.
Production-ready native Ruby batch inference for Cohere’s Arabic/English ASR model, with CPU/CUDA/Metal execution, Silero VAD, subtitles, and optional word-level timestamps.