Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Javanese
whisper
javanese
asr
Generated from Trainer
Eval Results (legacy)
Instructions to use bagasshw/asr_java_result_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bagasshw/asr_java_result_full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bagasshw/asr_java_result_full")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("bagasshw/asr_java_result_full") model = AutoModelForSpeechSeq2Seq.from_pretrained("bagasshw/asr_java_result_full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- a1e7efb62a7eadb7385d2ec9d2859207216abd6b1c24443460574d9951e2a444
- Size of remote file:
- 5.62 kB
- SHA256:
- 95865788465bef61a319ff99a9ef53b824ba237efda581c7e31292c6740ce319
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.