---

license: apache-2.0

language:

• it

pipeline_tag: automatic-speech-recognition

tags:

• audio
• speech-recognition
• transcription
• gguf
• wav2vec2
• crispasr
• italian

library_name: ggml

base_model: jonatasgrosman/wav2vec2-large-xlsr-53-italian

---

Wav2Vec2 Large Xlsr 53 Italian -- GGUF

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

Available variants

| File | Quant | Size | Notes |

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

| wav2vec2-large-xlsr-53-italian-f16.gguf | F16 | ~626 MB | Reference conversion |

| wav2vec2-large-xlsr-53-italian-q4_k.gguf | Q4_K | ~212 MB | Default auto-download target |

| wav2vec2-large-xlsr-53-italian-q8_0.gguf | Q8_0 | ~356 MB | Higher precision |

Model details

• Architecture: Wav2Vec2ForCTC
• Hidden size: 1024
• Attention heads: 16
• Transformer layers: 24
• CTC vocabulary: 44 tokens
• Language: Italian
• Base model: jonatasgrosman/wav2vec2-large-xlsr-53-italian

Usage with CrispASR

crispasr --backend wav2vec2 -m wav2vec2-large-xlsr-53-italian-q4_k.gguf -f audio.wav -l it

# Auto-download via registry alias once published:
crispasr --backend wav2vec2 -m auto --auto-download -l it -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-italian — 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.