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 โ€” 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
Downloads last month
35
GGUF
Model size
94.4M params
Architecture
wav2vec2
Hardware compatibility
Log In to add your hardware
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for cstr/wav2vec2-base-german-cv9-GGUF

Quantized
(1)
this model