README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - minds14
metrics:
  - accuracy
model-index:
  - name: intent_classify
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: minds14
          type: minds14
          config: en-US
          split: train
          args: en-US
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.061946902654867256

intent_classify

This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 2.7674
• Accuracy: 0.0619

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: 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_ratio: 0.1
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.98	14	2.6369	0.1062
No log	1.96	28	2.6476	0.0973
2.6346	2.95	42	2.6571	0.0973
2.6346	4.0	57	2.6573	0.0796
2.6206	4.98	71	2.6699	0.0708
2.6206	5.96	85	2.6687	0.0619
2.5993	6.95	99	2.6739	0.0619
2.5993	8.0	114	2.6755	0.0531
2.5752	8.98	128	2.6848	0.0619
2.5752	9.96	142	2.6820	0.0354
2.5487	10.95	156	2.6892	0.0354
2.5487	12.0	171	2.6989	0.0442
2.5112	12.98	185	2.7059	0.0354
2.5112	13.96	199	2.7208	0.0442
2.4728	14.95	213	2.7136	0.0442
2.4728	16.0	228	2.7208	0.0442
2.4331	16.98	242	2.7166	0.0265
2.4331	17.96	256	2.7288	0.0442
2.3926	18.95	270	2.7281	0.0354
2.3926	20.0	285	2.7297	0.0531
2.3926	20.98	299	2.7471	0.0531
2.341	21.96	313	2.7498	0.0619
2.341	22.95	327	2.7535	0.0619
2.2983	24.0	342	2.7534	0.0442
2.2983	24.98	356	2.7647	0.0442
2.2703	25.96	370	2.7696	0.0708
2.2703	26.95	384	2.7656	0.0531
2.238	28.0	399	2.7689	0.0619
2.238	28.98	413	2.7667	0.0619
2.213	29.47	420	2.7674	0.0619

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.2
• Datasets 2.12.0
• Tokenizers 0.13.2