whisper-base-th-newmm

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Whisper Base Thai Newmm Tokenized - Parinthapat Pengpun

This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 and the FLEURS datasets. It achieves the following results on the evaluation set:

• eval_loss: 0.5888
• eval_wer: 67.3381
• eval_cer: 32.4281
• eval_runtime: 6393.9778
• eval_samples_per_second: 1.709
• eval_steps_per_second: 0.214
• epoch: 1.0
• step: 2000

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: 1e-05
• 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
• training_steps: 7500
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu116
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2