skip to content
gigarouter gigarouter
models / speech-to-text · coming soon

wav2vec2-large-xlsr-53-greek

jonatasgrosman/wav2vec2-large-xlsr-53-greek

A popular open speech-to-text model, with 3.9M downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.

status
coming soon
API providers
0
downloads / mo
3.9M
license
apache-2.0

about this model

jonatasgrosman/wav2vec2-large-xlsr-53-greek is an automatic speech recognition (ASR) model fine-tuned for Greek, based on the Facebook wav2vec2-large-xlsr-53 architecture. It was trained on the train and validation splits of Common Voice 6.1 and CSS10, and requires 16 kHz sampled audio input.

Key capabilities

  • Recognizes spoken Greek across varied acoustic conditions, leveraging the cross-lingual pre-training of XLSR-53.
  • Optimized for direct use without an external language model.

Benchmark performance

On the Common Voice 6.1 Greek test set, the model achieves a Word Error Rate (WER) of 11.62% and a Character Error Rate (CER) of 3.36%. The following table compares it with other Greek ASR models evaluated under the same script:

ModelWERCER
lighteternal/wav2vec2-large-xlsr-53-greek10.13%2.66%
jonatasgrosman/wav2vec2-large-xlsr-53-greek11.62%3.36%
vasilis/wav2vec2-large-xlsr-53-greek19.09%5.88%
PereLluis13/wav2vec2-large-xlsr-53-greek20.16%5.71%

Best use cases

This model is well-suited for transcribing Greek speech in applications such as voice-to-text, media captioning, and conversational AI where accurate, real-time transcription is required.

not yet live

We're benchmarking and onboarding wav2vec2-large-xlsr-53-greek as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.