This model is a fine-tuned version of openai/whisper-large-v3 on the JacobLinCool/common_voice_19_0_zh-TW dataset.
It achieves the following results on the evaluation set:
eval_loss: 0.1502
eval_wer: 253.4012
eval_cer: 234.4286
eval_decode_runtime: 107.4219
eval_wer_runtime: 0.1395
eval_cer_runtime: 0.2215
eval_runtime: 352.6335
eval_samples_per_second: 14.216
eval_steps_per_second: 0.445
epoch: 2.1825
step: 4000
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: 0.0002
train_batch_size: 4
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
