wav2vec2-xls-r-juznevesti-sr

This model for Serbian ASR is based on the [facebook/wav2vec2-xls-r-300m model](https://huggingface.co/facebook/wav2vec2-xls-r-300m) and was fine-tuned with 58 hours of audio and transcripts from [Južne vesti](https://www.juznevesti.com/), programme '15 minuta'. For more info on the dataset creation see [this repo](https://github.com/clarinsi/parlaspeech/tree/main/juzne_vesti). Evaluation is performed on the dev and test portions of the JuzneVesti dataset Tested with `transformers==4.18.0`, `torch==1.11.0`, and `SoundFile==0.10.3.post1`. 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") processor = Wav2Vec2Processor.from_pretrained( "classla/wav2vec2-xls-r-juznevesti-sr") model = Wav2Vec2ForCTC.from_pretrained("classla/wav2vec2-xls-r-juznevesti-sr") os.system("wget https://huggingface.co/classla/wav2vec2-xls-r-parlaspeech-hr/raw/main/00020570a.flac.wav") speech, sample_rate = sf.read("00020570a.flac.wav") input_values = processor(speech, sampling_rate=sample_rate, return_tensors="pt").input_values.to(device) os.system("rm 00020570a.flac.wav") logits = model.to(device)(input_values).logits predicted_ids = torch.argmax(logits, dim=-1) transcription = processor.decode(predicted_ids[0]) transcription # 'velik broj poslovnih subjekata posluje sa minosom velik deo' In fine-tuning, the following arguments were used: