Downloads · 30 days
646
26% of all-time downloads
kyutai-stt-2.6b-en-GGUF
cstr/kyutai-stt-2.6b-en-GGUF
kyutai-stt-2.6b-en-GGUF is a automatic speech recognition model from cstr. Use it when you need speech turned into text. It is set up for moshi. The card lists the license as apache-2.0.
GGUF conversion of kyutai/stt-2.6b-en for the CrispASR kyutai-stt backend.
All-time downloads
2.5K
Public
Repo size
9.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf9.9 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- moshi
- License
- apache-2.0
- Access
- Public
- Created
- Jul 10, 2026
- Updated
- Jul 11, 2026
- SHA
- 6968d849
Base models
Model card
From the Hugging Face model README
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
| 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
# 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
- Task
- Automatic Speech Recognition
- Library
- moshi
- License
- apache-2.0
- Languages
- en
- Created
- Jul 10, 2026
- Updated
- Jul 11, 2026