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

Wav2Vec2 Large Xlsr 53 Portuguese -- GGUF

GGUF conversions and quantisations of `jonatasgrosman/wav2vec2-large-xlsr-53-portuguese` for use with [CrispStrobe/CrispASR](https://github.com/CrispStrobe/CrispASR).

Available variants

Model details

• —Architecture: Wav2Vec2ForCTC
• —Hidden size: 1024
• —Attention heads: 16
• —Transformer layers: 24
• —CTC vocabulary: 46 tokens
• —Language: Portuguese
• —Base model: jonatasgrosman/wav2vec2-large-xlsr-53-portuguese

Usage with CrispASR

crispasr --backend wav2vec2 -m wav2vec2-large-xlsr-53-portuguese-q4_k.gguf -f audio.wav -l pt

# Auto-download via registry alias once published:
crispasr --backend wav2vec2 -m auto --auto-download -l pt -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 — same as the upstream model card.

Provenance and EU AI Act Art. 53 note

• —Upstream model: jonatasgrosman/wav2vec2-large-xlsr-53-portuguese — published by jonatasgrosman.
• —Upstream licence: apache-2.0. 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/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.