classla_wav2vec2-xls-r-parlaspeech-hr

---

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/raw/main/1800.m4a
• example_title: example 2 src: https://huggingface.co/classla/wav2vec2-xls-r-parlaspeech-hr/raw/main/00020578b.flac.wav

---

wav2vec2-xls-r-parlaspeech-hr

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.

Notice: ParlaSpeech corpora are currently in the process of enrichment with new features. Follow our progress here: http://clarinsi.github.io/parlaspeech

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. http://www.lrec-conf.org/proceedings/lrec2022/workshops/ParlaCLARINIII/pdf/2022.parlaclariniii-1.16.pdf

Metrics

Evaluation is performed on the dev and test portions of the ParlaSpeech-HR v1.0 dataset.

split	CER	WER
dev	0.0335	0.1046
test	0.0234	0.0761

There are multiple models available, and in terms of CER and WER, the best-performing model is wav2vec2-large-slavic-parlaspeech-hr-lm.

Usage in transformers

from transformers import Wav2Vec2Processor, 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 = Wav2Vec2Processor.from_pretrained(
    "classla/wav2vec2-xls-r-parlaspeech-hr")
model = Wav2Vec2ForCTC.from_pretrained("classla/wav2vec2-xls-r-parlaspeech-hr")


# download the example wav files:
os.system("wget https://huggingface.co/classla/wav2vec2-xls-r-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.to(device)

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

# retrieve logits
logits = model.to(device)(input_values).logits

# take argmax and decode
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.decode(predicted_ids[0]).lower()

# transcription: 'veliki 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