---
language: hr
datasets:
- parlaspeech-hr
tags:
- audio
- automatic-speech-recognition
- parlaspeech
widget:
- example_title: example 1
  src: https://huggingface.co./classla/wav2vec2-xls-r-parlaspeech-hr-lm/raw/main/1800.m4a
- example_title: example 2
  src: https://huggingface.co./classla/wav2vec2-xls-r-parlaspeech-hr-lm/raw/main/00020578b.flac.wav
- example_title: example 3
  src: https://huggingface.co./classla/wav2vec2-xls-r-parlaspeech-hr-lm/raw/main/00020570a.flac.wav
---

# wav2vec2-xls-r-parlaspeech-hr-lm

This model for Croatian ASR is based on the [facebook/wav2vec2-xls-r-300m model](https://huggingface.co./facebook/wav2vec2-xls-r-300m) and was fine-tuned with 300 hours of recordings and transcripts from the ASR Croatian parliament dataset [ParlaSpeech-HR v1.0](http://hdl.handle.net/11356/1494).

If you use this model, please cite the following paper:

Nikola Ljubešić, Danijel Koržinek, Peter Rupnik, Ivo-Pavao Jazbec. ParlaSpeech-HR -- a freely available ASR dataset for Croatian bootstrapped from the ParlaMint corpus. Accepted at ParlaCLARIN@LREC.

## Metrics

Evaluation is performed on the dev and test portions of the [ParlaSpeech-HR v1.0](http://hdl.handle.net/11356/1494) dataset.

|split|CER|WER|
|---|---|---|
|dev|0.0448|0.1129|
|test|0.0363|0.0985|


## Usage in `transformers`

Tested with `transformers==4.18.0`, `torch==1.11.0`, and `SoundFile==0.10.3.post1`.


```python
from transformers import Wav2Vec2ProcessorWithLM, Wav2Vec2ForCTC
import soundfile as sf
import torch
import os
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# load model and tokenizer
processor = Wav2Vec2ProcessorWithLM.from_pretrained(
    "classla/wav2vec2-xls-r-parlaspeech-hr-lm")
model = Wav2Vec2ForCTC.from_pretrained("classla/wav2vec2-xls-r-parlaspeech-hr-lm")
# download the example wav files:
os.system("wget https://huggingface.co./classla/wav2vec2-large-slavic-parlaspeech-hr/raw/main/00020570a.flac.wav")
# read the wav file 
speech, sample_rate = sf.read("00020570a.flac.wav")
input_values = processor(speech, sampling_rate=sample_rate, return_tensors="pt").input_values.cuda()
inputs = processor(speech, sampling_rate=sample_rate, return_tensors="pt")
with torch.no_grad():
    logits = model(**inputs).logits
transcription = processor.batch_decode(logits.numpy()).text[0]

# remove the raw wav file
os.system("rm 00020570a.flac.wav")
transcription

# transcription: 'velik broj poslovnih subjekata posluje sa minusom velik dio'
```



## Training hyperparameters

In fine-tuning, the following arguments were used:

| arg                           | value |
|-------------------------------|-------|
| `per_device_train_batch_size` | 16    |
| `gradient_accumulation_steps` | 4     |
| `num_train_epochs`            | 8     |
| `learning_rate`               | 3e-4  |
| `warmup_steps`                | 500   |