Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("Jana0511/wav2vec2-large-xls-r-300m-welsh-colab")
model = AutoModelForCTC.from_pretrained("Jana0511/wav2vec2-large-xls-r-300m-welsh-colab", device_map="auto")Quick Links
wav2vec2-large-xls-r-300m-welsh-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 2.0522
- Wer: 0.9999
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: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.6024 | 2.26 | 400 | 2.0522 | 0.9999 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 4
Model tree for Jana0511/wav2vec2-large-xls-r-300m-welsh-colab
Base model
facebook/wav2vec2-xls-r-300mDataset used to train Jana0511/wav2vec2-large-xls-r-300m-welsh-colab
Evaluation results
- Wer on common_voicetest set self-reported1.000
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Jana0511/wav2vec2-large-xls-r-300m-welsh-colab")