whisper-diarization-0.2

This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5895
• eval_speech_scored: 619.9204
• eval_speech_miss: 375.8010
• eval_speech_falarm: 214.8806
• eval_speaker_miss: 891.5274
• eval_speaker_falarm: 215.0796
• eval_speaker_error: 136.2537
• eval_speaker_correct: 1040.2952
• eval_diarization_error: 1242.8607
• eval_frames: 1500.0
• eval_speaker_wide_frames: 1511.7811
• eval_speech_scored_ratio: 0.4133
• eval_speech_miss_ratio: 0.2505
• eval_speech_falarm_ratio: 0.1433
• eval_speaker_correct_ratio: 0.6935
• eval_speaker_miss_ratio: 0.5219
• eval_speaker_falarm_ratio: 0.5440
• eval_speaker_error_ratio: 0.0796
• eval_diarization_error_ratio: 1.1455
• eval_runtime: 2.2469
• eval_samples_per_second: 89.456
• eval_steps_per_second: 4.006
• epoch: 3.0
• step: 36

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: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 10
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.0
• Datasets 2.16.1
• Tokenizers 0.15.0