metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- ml-superb-subset
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-ssw
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: ml-superb-subset
type: ml-superb-subset
config: ssw
split: dev
args: ssw
metrics:
- name: Wer
type: wer
value: 0.9968847352024922
wav2vec2-large-xls-r-ssw
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the ml-superb-subset dataset. It achieves the following results on the evaluation set:
- Loss: 1.4697
- Wer: 0.9969
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.3138 | 1.0471 | 100 | 4.7003 | 1.0 |
| 3.1815 | 2.0942 | 200 | 3.1195 | 1.0 |
| 3.1618 | 3.1414 | 300 | 3.1440 | 1.0 |
| 3.068 | 4.1885 | 400 | 3.2146 | 1.0 |
| 3.0495 | 5.2356 | 500 | 3.0380 | 1.0 |
| 2.9972 | 6.2827 | 600 | 2.9489 | 1.0 |
| 2.6887 | 7.3298 | 700 | 2.5815 | 1.0 |
| 2.2022 | 8.3770 | 800 | 1.9518 | 1.0 |
| 1.6504 | 9.4241 | 900 | 1.4697 | 0.9969 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1