Instructions to use nlw9898/successor-basic-distorted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nlw9898/successor-basic-distorted with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nlw9898/successor-basic-distorted")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("nlw9898/successor-basic-distorted") model = AutoModelForCTC.from_pretrained("nlw9898/successor-basic-distorted", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from nlw9898/successor-basic-distorted: direct link, hf CLI and curl.
- Browser
- Download file 1.52 kB
-
https://huggingface.co/nlw9898/successor-basic-distorted/resolve/refs%2Fpr%2F1/README.md
- Command line
-
hf download hf://nlw9898/successor-basic-distorted@refs/pr/1/README.md
-
curl -L -o README.md https://huggingface.co/nlw9898/successor-basic-distorted/resolve/refs%2Fpr%2F1/README.md
1.52 kB
| license: apache-2.0 | |
| tags: | |
| - generated_from_trainer | |
| metrics: | |
| - wer | |
| model-index: | |
| - name: nlw9898/successor-basic-distorted | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # nlw9898/successor-basic-distorted | |
| This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.3230 | |
| - Wer: 0.1978 | |
| ## Model description | |
| More information needed | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 0.0003 | |
| - train_batch_size: 8 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 4 | |
| - total_train_batch_size: 32 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - lr_scheduler_warmup_steps: 500 | |
| - num_epochs: 30 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Wer | | |
| |:-------------:|:-----:|:----:|:---------------:|:------:| | |
| | 2.8945 | 12.8 | 400 | 0.5006 | 0.3171 | | |
| | 0.2089 | 25.6 | 800 | 0.3230 | 0.1978 | | |
| ### Framework versions | |
| - Transformers 4.30.2 | |
| - Pytorch 2.0.1+cu118 | |
| - Datasets 1.18.3 | |
| - Tokenizers 0.13.3 | |