## 🎤 Audio Transcription (ASR / STT) - https://huggingface.co/distil-whisper/distil-large-v3.5 - https://huggingface.co/zai-org/GLM-ASR-Nano-2512 - https://huggingface.co/kyutai/stt-2.6b-en - https://huggingface.co/microsoft/VibeVoice-ASR - https://huggingface.co/microsoft/VibeVoice-ASR-HF - https://github.com/microsoft/VibeVoice/blob/main/docs/vibevoice-realtime-0.5b.md - https://huggingface.co/microsoft/VibeVoice-ASR-HF/tree/main - https://huggingface.co/UsefulSensors/moonshine-streaming-medium - https://huggingface.co/UsefulSensors/moonshine-streaming-small - https://huggingface.co/UsefulSensors/moonshine-streaming-tiny - https://huggingface.co/nvidia/parakeet-unified-en-0.6b - https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602 - https://huggingface.co/CohereLabs/cohere-transcribe-03-2026 - https://huggingface.co/openbmb/VoxCPM2 - https://huggingface.co/ibm-granite/granite-speech-4.1-2b - https://huggingface.co/ibm-granite/granite-speech-4.1-2b-plus - https://huggingface.co/ibm-granite/granite-speech-4.1-2b-nar - https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b ## ⭐ Exceptional - https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2 (slightly less quality than canary but way faster) - https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3 (slightly less quality than canary but way faster) ## ✅ Good - https://huggingface.co/nvidia/canary-qwen-2.5b (heavy but supposedly higher accuracy than parakeet) - https://huggingface.co/ibm-granite/granite-4.0-1b-speech (very heavy but supposedly higher accuracy than canary) ## ❌ Unacceptable/Deprecated - ~https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b~ (outdated)
🎤 Audio Transcription (ASR / STT)
⭐ Exceptional
✅ Good
❌ Unacceptable/Deprecated
https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b(outdated)