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/main/README.md
- Command line
-
hf download hf://nlw9898/successor-basic-distorted/README.md
-
curl -L -o README.md https://huggingface.co/nlw9898/successor-basic-distorted/resolve/main/README.md
1.52 kB
metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: nlw9898/successor-basic-distorted
results: []
nlw9898/successor-basic-distorted
This model is a fine-tuned version of 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