AI · Collection
Fine Tune Candidates 1026
Candidates for a fine tuning idea for audio to text with deterministic post processing edits applied in one forward pass
13 models
- model nvidia/canary-1b
- model Qwen/Qwen3-ASR-1.7B-hf
- model nvidia/nemotron-3.5-asr-streaming-0.6b
- model nvidia/parakeet-tdt-0.6b-v3
- model mistralai/Voxtral-Mini-4B-Realtime-2602
- model Qwen/Qwen3-ASR-0.6B
- model ibm-granite/granite-speech-4.1-2b
- model kyutai/stt-2.6b-en
- model XiaomiMiMo/MiMo-V2.5-ASR
- model oruk/orukeet
- model moondream/parakeet-ultra
- model moonshine-ai/moonshine
- model microsoft/VibeVoice-ASR-Streaming-1.5B
Copied from Hugging Face on 7 November 2026.