---

license: cc-by-4.0

tags: [gguf, asr, speech-recognition, fastconformer, english, crispembed]

base_model: nvidia/parakeet-tdt-0.6b-v2

library_name: crispasr

pipeline_tag: automatic-speech-recognition

---

Parakeet Unified EN 0.6B — GGUF

GGUF conversion of NVIDIA's Parakeet TDT 0.6B v2 for CrispASR.

FastConformer-based English ASR with Token-and-Duration Transducer (TDT) decoder. 600M params.

Models

| File | Quant | Size |

|------|-------|------|

| parakeet-unified-en-0.6b-f16.gguf | F16 | ~1.2 GB |

| parakeet-unified-en-0.6b-q4_k.gguf | Q4_K | ~350 MB |

Usage

crispasr --model parakeet-unified-en-0.6b-q4_k.gguf audio.wav

License

CC-BY-4.0 (nvidia/parakeet-tdt-0.6b-v2)

Provenance and EU AI Act Art. 53 note

• Upstream model: nvidia/parakeet-tdt-0.6b-v2 — published by nvidia.
• Upstream licence: cc-by-4.0. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
• What was done here: format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
• Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
• Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.