Edit model card

wav2vec2-common_voice-ps-demo

This model is a fine-tuned version of ylacombe/w2v-bert-2.0 on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - PS dataset. It achieves the following results on the evaluation set:

  • Loss: 3.0510
  • Wer: 0.9484

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • 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: 500
  • num_epochs: 15.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 3.08 100 10.3691 1.0
No log 6.15 200 3.5670 1.0
No log 9.23 300 3.1139 0.9484
No log 12.31 400 3.0949 0.9484

Framework versions

  • Transformers 4.37.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.5
  • Tokenizers 0.15.0
Downloads last month
3
Safetensors
Model size
581M 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 ylacombe/wav2vec2-common_voice-ps-demo

Finetuned
(16)
this model

Evaluation results