Automatic Speech Recognition
Transformers
PyTorch
Safetensors
English
wav2vec2
audio
en-atc
Generated from Trainer
Eval Results (legacy)
Instructions to use Jzuluaga/wav2vec2-large-960h-lv60-self-en-atc-atcosim with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jzuluaga/wav2vec2-large-960h-lv60-self-en-atc-atcosim with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Jzuluaga/wav2vec2-large-960h-lv60-self-en-atc-atcosim")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Jzuluaga/wav2vec2-large-960h-lv60-self-en-atc-atcosim") model = AutoModelForCTC.from_pretrained("Jzuluaga/wav2vec2-large-960h-lv60-self-en-atc-atcosim", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 256.41, | |
| "eval_loss": 0.08499366790056229, | |
| "eval_runtime": 68.056, | |
| "eval_samples": 1857, | |
| "eval_samples_per_second": 27.286, | |
| "eval_steps_per_second": 1.146, | |
| "eval_wer": 0.016747895436420027 | |
| } |