This wav2vec2 model is fine-tuned on the ParlaSpeech-HR corpus for automatic speech recognition in Croatian. Provided by CLASSLA (CLARIN Knowledge Centre), it can be used via the Transformers library for local inference. It is designed for researchers and developers working with South Slavic languages and public speech data.
In the Voice, TTS & speech space, Wav2vec2 Xls R Parlaspeech Hr takes a focused approach. It focuses on transcribing Croatian parliamentary and spoken audio into text. Wav2vec2 Xls R Parlaspeech Hr is an open-source project aimed at developers. The project is open source (Open Source). Wav2vec2 Xls R Parlaspeech Hr is available on the web and API.
CLASSLA builds and maintains Wav2vec2 Xls R Parlaspeech Hr, and it first shipped in 2023. Key capabilities include Automatic Speech Recognition, Transformers Compatible, and Model Card.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do