Hugging Face's logo

zainulhakim
/
240801-wav2vec2-ASR-Global-All-Clients

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
240801-wav2vec2-ASR-Global-All-Clients / README.md
zainulhakim's picture
zainulhakim
End of training
9778968 verified
preview code
|
raw
history blame
No virus
3.16 kB
metadata
license: apache-2.0
base_model: zainulhakim/240626-wav2vec2-ASR_Global
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: 240801-wav2vec2-ASR-Global-All-Clients
    results: []

Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases

240801-wav2vec2-ASR-Global-All-Clients

This model is a fine-tuned version of zainulhakim/240626-wav2vec2-ASR_Global on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.0444
  • Wer: 0.9977

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: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 1.2658 100 3.0729 1.0
No log 2.5316 200 3.0444 0.9977
No log 3.7975 300 3.0218 1.0

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1