Wav2Vec2 Base German (CV9) -- GGUF
GGUF conversions and quantisations of oliverguhr/wav2vec2-base-german-cv9 for use with CrispStrobe/CrispASR.
Available variants
| File | Quant | Size | Notes |
|---|---|---|---|
wav2vec2-base-german-cv9-q4_k.gguf |
Q4_K | ~60 MB | Best size/quality tradeoff |
Model details
- Architecture: Wav2Vec2ForCTC — CNN feature extractor + 12L transformer encoder (768d, 12 heads, post-norm) + CTC head
- Parameters: 94M
- Language: German
- Vocab: 35 characters (CTC greedy decode)
- License: MIT
- Source:
oliverguhr/wav2vec2-base-german-cv9 - Small and fast. MIT licensed. Post-norm architecture (wav2vec2-base style).
Usage with CrispASR
./build/bin/crispasr --backend wav2vec2 -m wav2vec2-base-german-cv9-q4_k.gguf -f german_audio.wav -l de
# Auto-download (default German model):
./build/bin/crispasr --backend wav2vec2 -m auto --auto-download -l de -f audio.wav
Provenance and EU AI Act Art. 53 note
- Upstream model: oliverguhr/wav2vec2-base-german-cv9 — published by
oliverguhr. - Upstream licence:
mit. 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/GGML). 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.