CoolFace
Modelpublic

cstr/kyutai-stt-2.6b-en-GGUF

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes720downloads
Model Card

Kyutai STT 2.6B English — GGUF

GGUF conversion of kyutai/stt-2.6b-en for the CrispASR kyutai-stt backend.

High-quality English ASR from the Kyutai/Moshi team. Causal transformer LM conditioned on Mimi audio codec features — streaming-capable architecture.

Architecture

  • —Mimi encoder: SEANet CNN + transformer + RVQ (audio -> discrete tokens)
  • —Causal LM: 16-layer transformer (2048-dim, RoPE, SwiGLU, RMSNorm)
  • —Input: 16 kHz mono audio
  • —Output: English text transcription

Files

FileSizeDescription
kyutai-stt-2.6b-q4_k.gguf1.5 GBQ4_K quantized (recommended)
kyutai-stt-2.6b-q8_0.gguf2.8 GBQ8_0 quantized
kyutai-stt-2.6b-f16.gguf5.1 GBF16 full precision
kyutai-stt-2.6b-ref.gguf4.0 MBDiff harness reference

Usage

bash
# Auto-download:
crispasr --backend kyutai-stt -m auto --auto-download -f audio.wav

# Local model:
crispasr --backend kyutai-stt -m kyutai-stt-2.6b-q4_k.gguf -f audio.wav -osrt

License

Apache 2.0 (same as the original model).

Credits