A fine-tuned version of the XLSR-53 wav2vec2 model specialized for Greek automatic speech recognition. It can be used with the Hugging Face Transformers library to transcribe Greek audio. The model was trained on Common Voice data and is suitable for research and application development involving Greek speech.
Wav2vec2 Large Xlsr 53 Greek sits in PulseGate's Voice, TTS & speech category. It focuses on transcribing Greek speech to text without training a custom ASR model. It is built as an open-source project for developers. Wav2vec2 Large Xlsr 53 Greek is open source under the Apache-2.0 license. It runs on the web and API.
It is developed by Jonatas Grosman, and it first shipped in 2018. Development happens publicly on GitHub with 490 stars. It operates in a well-populated space: PulseGate tracks 8 similar projects. Among its 4 catalogued features are Automatic Speech Recognition, Greek Language, and wav2Vec2.
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