|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: checkpoints2 |
|
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. --> |
|
|
|
# checkpoints2 |
|
|
|
This model is a fine-tuned version of [ttop324/wav2vec2-live-japanese](https://huggingface.co/ttop324/wav2vec2-live-japanese) on the extracted and cleaned transcript of [Holo No Graffiti](https://youtube.com/playlist?list=PLS51cvjOMUKwKtxe_IxhbBBvQ9XpiL1W_) |
|
dataset. |
|
|
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
Evaluated from [common_voice | train | ja ](https://huggingface.co/datasets/common_voice/viewer/ja/test): |
|
- WER: 32.940524 |
|
- CER: 15.251746 |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0003 |
|
- train_batch_size: 3 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 6 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 1.18.3 |
|
- Tokenizers 0.12.1 |
|
|
