metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- common_voice_1_0
metrics:
- wer
model-index:
- name: DynamicWav2Vec_TEST_10
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_1_0
type: common_voice_1_0
config: it
split: test
args: it
metrics:
- name: Wer
type: wer
value: 1
DynamicWav2Vec_TEST_10
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_1_0 dataset. It achieves the following results on the evaluation set:
- Loss: 2.9344
- Wer: 1.0
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.5792 | 2.68 | 400 | 2.9642 | 1.0 |
| 2.9539 | 5.35 | 800 | 2.9882 | 1.0 |
| 2.9476 | 8.03 | 1200 | 3.0384 | 1.0 |
| 2.9497 | 10.7 | 1600 | 2.9524 | 1.0 |
| 2.9562 | 13.38 | 2000 | 2.9332 | 1.0 |
| 2.945 | 16.05 | 2400 | 2.9858 | 1.0 |
| 2.9383 | 18.73 | 2800 | 2.9419 | 1.0 |
| 2.9311 | 21.4 | 3200 | 2.9328 | 1.0 |
| 2.9298 | 24.08 | 3600 | 2.9375 | 1.0 |
| 2.9273 | 26.76 | 4000 | 2.9352 | 1.0 |
| 2.921 | 29.43 | 4400 | 2.9344 | 1.0 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3