Downloads · 30 days
42
6% of all-time downloads
wav2vec2-japanese-vtuber
thunninoi/wav2vec2-japanese-vtuber
wav2vec2-japanese-vtuber is a automatic speech recognition model from thunninoi. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
652
Public
Repo size
3.8 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- May 27, 2022
- Updated
- Jul 8, 2022
- SHA
- 1d9c01d1
Model card
From the Hugging Face model README
<!-- 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 on the extracted and cleaned transcript of Holo No Graffiti dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Evaluated from common_voice | train | ja :
- 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
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- May 27, 2022
- Updated
- Jul 8, 2022