Kyutai Stt 2.6b En GGUF

--- language: en license: apache-2.0 tags: - gguf - asr - speech-recognition - streaming - kyutai - moshi - crispasr base_model: kyutai/stt-2.6b-en pipeline_tag: automatic-speech-recognition --- # Kyutai STT 2.6B English — GGUF GGUF conversion of [kyutai/stt-2.6b-en](https://huggingface.co/kyutai/stt-2.6b-en) for the [CrispASR](https://github.com/CrispStrobe/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 | File | Size | Description | |------|------|-------------| | `kyutai-stt-2.6b-q4_k.gguf` | 1.5 GB | Q4_K quantized (recommended) | | `kyutai-stt-2.6b-q8_0.gguf` | 2.8 GB | Q8_0 quantized | | `kyutai-stt-2.6b-f16.gguf` | 5.1 GB | F16 full precision | | `kyutai-stt-2.6b-ref.gguf` | 4.0 MB | Diff 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 - Original model: [Kyutai](https://huggingface.co/kyutai/stt-2.6b-en) - GGUF conversion & runtime: [CrispASR](https://github.com/CrispStrobe/CrispASR)

Source context: 501 downloads · 0 likes · Pipeline automatic-speech-recognition · Library moshi · Repo cstr/kyutai-stt-2.6b-en-GGUF