wav2vec2_tiny_ja_roman

This model is a fine-tuned version of charsiu/zh_w2v2_tiny_fc_10ms on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.0716
  • eval_wer: 0.5521
  • eval_runtime: 26.495
  • eval_samples_per_second: 9.436
  • eval_steps_per_second: 1.208
  • epoch: 30.0
  • step: 4455

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: 0.0001
  • 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_steps: 742
  • num_epochs: 50

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
14
Safetensors
Model size
23.3M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for trtd56/wav2vec2_tiny_ja_roman

Finetuned
(1)
this model