Instructions to use ThomasFG/Baseline-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ThomasFG/Baseline-FT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ThomasFG/Baseline-FT")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("ThomasFG/Baseline-FT") model = AutoModelForSpeechSeq2Seq.from_pretrained("ThomasFG/Baseline-FT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| {"pretrained_model": "openai/whisper-small.en", "dataset_path": "./data", "output_dir": "./fine-tuned-whisper", "num_train_epochs": 1, "train_batch_size": 64, "gradient_accumulation_steps": 1, "eval_batch_size": 8, "max_learning_rate": 1e-05, "warmup_steps": 0, "max_steps": 0, "eval_steps": null, "gradient_checkpointing": true, "fp16": true, "evaluation_strategy": "epoch", "logging_steps": 500, "save_steps": 1000, "dataset": "myst", "real": 0, "fake": 0, "patience": 5} |