Automatic Speech Recognition
Transformers
PyTorch
data2vec-audio
abdusahmbzuai/arabic_speech_massive_300hrs
Generated from Trainer
Instructions to use abdusah/aradia-ctc-data2vec-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abdusah/aradia-ctc-data2vec-ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="abdusah/aradia-ctc-data2vec-ft")# Load model directly from transformers import AutoTokenizer, AutoModelForCTC tokenizer = AutoTokenizer.from_pretrained("abdusah/aradia-ctc-data2vec-ft") model = AutoModelForCTC.from_pretrained("abdusah/aradia-ctc-data2vec-ft", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download train_results.json from abdusah/aradia-ctc-data2vec-ft: direct link, hf CLI and curl.
- Browser
- Download file 195 Bytes
-
https://huggingface.co/abdusah/aradia-ctc-data2vec-ft/resolve/main/train_results.json
- Command line
-
hf download hf://abdusah/aradia-ctc-data2vec-ft/train_results.json
-
curl -L -o train_results.json https://huggingface.co/abdusah/aradia-ctc-data2vec-ft/resolve/main/train_results.json
195 Bytes
| { | |
| "epoch": 30.0, | |
| "train_loss": 0.04483215774314991, | |
| "train_runtime": 852.37, | |
| "train_samples": 14730, | |
| "train_samples_per_second": 518.437, | |
| "train_steps_per_second": 8.095 | |
| } |