wav2vec2-large-xlsr-53-hungarian
jonatasgrosman/wav2vec2-large-xlsr-53-hungarian
A popular open speech-to-text model, with 3.4M downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.
about this model
jonatasgrosman/wav2vec2-large-xlsr-53-hungarian is an automatic speech recognition (ASR) model fine-tuned for Hungarian from Facebook's wav2vec2-large-xlsr-53. It was trained on the train and validation splits of Common Voice 6.1 and the CSS10 Hungarian dataset. The model expects speech input sampled at 16 kHz.
Key strengths
- Fine-tuned specifically for Hungarian, achieving strong performance on the Common Voice Hungarian test set.
- Outperforms other publicly available Hungarian XLSR-53 models in both word error rate (WER) and character error rate (CER).
Benchmark results
Evaluated on the Common Voice Hungarian test set (2021-04-22):
| Model | WER | CER |
|---|---|---|
| jonatasgrosman/wav2vec2-large-xlsr-53-hungarian | 31.40% | 6.20% |
| anton-l/wav2vec2-large-xlsr-53-hungarian | 42.39% | 9.39% |
| gchhablani/wav2vec2-large-xlsr-hu | 46.42% | 10.04% |
| birgermoell/wav2vec2-large-xlsr-hungarian | 46.93% | 10.31% |
Best for
This model is suitable for production ASR pipelines in Hungarian where low word and character error rates are critical. Gigarouter hosts it as a managed, OpenAI-compatible API—no infrastructure or model loading code required.
We're benchmarking and onboarding wav2vec2-large-xlsr-53-hungarian 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.