Instructions to use oluwagbotty/mms_eng_yor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oluwagbotty/mms_eng_yor with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="oluwagbotty/mms_eng_yor")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("oluwagbotty/mms_eng_yor") model = AutoModelForCTC.from_pretrained("oluwagbotty/mms_eng_yor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.243605359317905, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.243605359317905, | |
| "grad_norm": 33.11063766479492, | |
| "learning_rate": 4.8844282238442824e-05, | |
| "loss": 10.7343, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.243605359317905, | |
| "eval_loss": 4.385446548461914, | |
| "eval_runtime": 206.0799, | |
| "eval_samples_per_second": 7.992, | |
| "eval_steps_per_second": 1.0, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4110, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3886859247161754e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |