Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
abdusahmbzuai/arabic_speech_massive_300hrs
Generated from Trainer
Instructions to use abdusah/aradia-ctc-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abdusah/aradia-ctc-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="abdusah/aradia-ctc-v1", device_map="auto")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("abdusah/aradia-ctc-v1") model = AutoModelForCTC.from_pretrained("abdusah/aradia-ctc-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 382 Bytes
3637072 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | {
"epoch": 14.78,
"eval_loss": 0.717069685459137,
"eval_runtime": 202.6594,
"eval_samples": 4899,
"eval_samples_per_second": 24.174,
"eval_steps_per_second": 0.76,
"eval_wer": 0.333567605557658,
"train_loss": 0.0,
"train_runtime": 70.228,
"train_samples": 14730,
"train_samples_per_second": 4194.91,
"train_steps_per_second": 65.501
} |