README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - bayartsogt/mongolian_speech_commands
model-index:
  - name: wav2vec2-base-mn-pretrain-42h-mn-silence-speech-commands
    results: []

wav2vec2-base-mn-pretrain-42h-mn-silence-speech-commands

This model is a fine-tuned version of bayartsogt/wav2vec2-base-mn-pretrain-42h on the Mongolian Speech Commands dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1148
• eval_mn_acc: 0.9716
• eval_mn_f1: 0.9719
• eval_silence_acc: 1.0
• eval_silence_f1: 1.0
• eval_runtime: 15.5961
• eval_samples_per_second: 37.445
• eval_steps_per_second: 0.321
• epoch: 3.2
• step: 64

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: 5e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 8

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3