Automatic Speech Recognition
Transformers
PyTorch
Indonesian
wav2vec2
hf-asr-leaderboard
mozilla-foundation/common_voice_8_0
robust-speech-event
Eval Results (legacy)
Instructions to use Wikidepia/wav2vec2-xls-r-300m-indonesian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Wikidepia/wav2vec2-xls-r-300m-indonesian with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Wikidepia/wav2vec2-xls-r-300m-indonesian")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Wikidepia/wav2vec2-xls-r-300m-indonesian") model = AutoModelForCTC.from_pretrained("Wikidepia/wav2vec2-xls-r-300m-indonesian", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Wav2Vec2 XLS-R-300M - Indonesian
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the mozilla-foundation/common_voice_8_0 and MagicHub Indonesian Conversational Speech Corpus.
- Downloads last month
- 9,065
Model tree for Wikidepia/wav2vec2-xls-r-300m-indonesian
Evaluation results
- Test WER on Common Voice 8self-reported5.046
- Test CER on Common Voice 8self-reported1.699
- Test WER on Robust Speech Event - Dev Dataself-reported41.310
- Test WER on Robust Speech Event - Test Dataself-reported52.230