Automatic Speech Recognition
Transformers
PyTorch
JAX
Oriya
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results (legacy)
Instructions to use anuragshas/wav2vec2-large-xlsr-53-odia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anuragshas/wav2vec2-large-xlsr-53-odia with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="anuragshas/wav2vec2-large-xlsr-53-odia")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("anuragshas/wav2vec2-large-xlsr-53-odia") model = AutoModelForCTC.from_pretrained("anuragshas/wav2vec2-large-xlsr-53-odia") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 199.94, | |
| "eval_loss": 1.0759512186050415, | |
| "eval_mem_cpu_alloc_delta": 12901181, | |
| "eval_mem_cpu_peaked_delta": 845619, | |
| "eval_mem_gpu_alloc_delta": 0, | |
| "eval_mem_gpu_peaked_delta": 1679536640, | |
| "eval_runtime": 4.9907, | |
| "eval_samples": 98, | |
| "eval_samples_per_second": 19.637, | |
| "eval_wer": 0.857916102841678 | |
| } |