cstr/wav2vec2-large-xlsr-53-spanish-GGUF

Wav2Vec2 Large Xlsr 53 Spanish -- GGUF

GGUF conversions and quantisations of jonatasgrosman/wav2vec2-large-xlsr-53-spanish for use with CrispStrobe/CrispASR.

Available variants

File	Quant	Size	Notes
wav2vec2-large-xlsr-53-spanish-f16.gguf	F16	~0 MB	Reference conversion
wav2vec2-large-xlsr-53-spanish-q4_k.gguf	Q4_K	~0 MB	Default auto-download target
wav2vec2-large-xlsr-53-spanish-q8_0.gguf	Q8_0	~0 MB	Higher precision

Model details

• Architecture: Wav2Vec2ForCTC
• Hidden size: 1024
• Attention heads: 16
• Transformer layers: 24
• CTC vocabulary: 41 tokens
• Language: Spanish
• Base model: jonatasgrosman/wav2vec2-large-xlsr-53-spanish

Usage with CrispASR

crispasr --backend wav2vec2 -m wav2vec2-large-xlsr-53-spanish-q4_k.gguf -f audio.wav -l es

# Auto-download via registry alias once published:
crispasr --backend wav2vec2 -m auto --auto-download -l es -f audio.wav

Provenance

Converted from the upstream Hugging Face checkpoint with models/convert-wav2vec2-to-gguf.py, then quantized with build-ninja-compile/bin/crispasr-quantize.

License

APACHE-2.0 — inherited from the upstream model card.