tiny-audio, nanoGPT for speech-to-text

Automated excerpt

Overlap The model card covers batching and GPU settings. 4090). JSON body: to send JSON instead, use {"inputs": "<base64 audio>", "parameters": {... }}. Other endpoints: GET /health and GET /stats (batch sizes and GPU time). than 100 seconds.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.