classla / automatic-speech-recognition updated 1 year ago

wav2vec2-xls-r-parlaspeech-hr

Name: wav2vec2-xls-r-parlaspeech-hr
Author: classla

This model for Croatian ASR is based on the facebook/wav2vec2-xls-r-300m model and was fine-tuned with 300 hours of recordings and transcripts from the ASR Croatian parliament dataset ParlaSpeech-HR v1.0.

Params

320 M

Context

—

Downloads 30d

564 K

Likes

Licence: unknown Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

711 K478 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	1.3 GB	1.9 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Wav2Vec2ForCTC
Parameters: 320 M
Tensor type: F32
Vocabulary: 50
Layers / heads: 24 / 16
First seen on the Hub: 2022-03-02
Training datasets: parlaspeech-hr
Added to our catalog: 2026-07-28

Compare with

speaker-diarization-3.1 8.9 M whisperkit-coreml 8.3 M whisper-large-v3 5.5 M speaker-diarization-community-1 5.3 M whisper-base 4.8 M wav2vec2-large-xlsr-53-portuguese 4.6 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB