| --- |
| library_name: transformers |
| language: |
| - ja |
| license: apache-2.0 |
| base_model: utakumi/Hubert-common_voice-phoneme-ctc_zero_infinity |
| tags: |
| - automatic-speech-recognition |
| - mozilla-foundation/common_voice_13_0 |
| - generated_from_trainer |
| datasets: |
| - common_voice_13_0 |
| model-index: |
| - name: Hubert-ft-eval |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| # Hubert-ft-eval |
|
|
| This model is a fine-tuned version of [utakumi/Hubert-common_voice-phoneme-ctc_zero_infinity](https://huggingface.co/utakumi/Hubert-common_voice-phoneme-ctc_zero_infinity) on the MOZILLA-FOUNDATION/COMMON_VOICE_13_0 - JA dataset. |
| It achieves the following results on the evaluation set: |
| - eval_loss: 0.6036 |
| - eval_model_preparation_time: 0.0038 |
| - eval_wer: 1.0 |
| - eval_cer: 0.1999 |
| - eval_runtime: 205.0868 |
| - eval_samples_per_second: 24.18 |
| - eval_steps_per_second: 3.023 |
| - step: 0 |
|
|
| ## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 12500 |
| - num_epochs: 1.0 |
| - mixed_precision_training: Native AMP |
|
|
| ### Framework versions |
|
|
| - Transformers 4.47.0.dev0 |
| - Pytorch 2.5.1+cu124 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
|
|
