librarian-bot's picture
Librarian Bot: Add base_model information to model
46b42f2
|
raw
history blame
1.81 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - speech_commands
metrics:
  - accuracy
base_model: facebook/wav2vec2-base
model-index:
  - name: wav2vec2-base-finetuned-speech_commands-v0.02
    results: []

wav2vec2-base-finetuned-speech_commands-v0.02

This model is a fine-tuned version of facebook/wav2vec2-base on the speech_commands dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1170
  • Accuracy: 0.9759

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: 3e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.9963 1.0 663 0.7316 0.9612
0.4965 2.0 1326 0.2656 0.9672
0.4306 3.0 1989 0.1630 0.9720
0.2901 4.0 2652 0.1283 0.9753
0.2963 5.0 3315 0.1170 0.9759

Framework versions

  • Transformers 4.27.4
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3