Downloads · 30 days
17
5% of all-time downloads
wav2vec2-large-xls-r-300m-ja-colab
pinot/wav2vec2-large-xls-r-300m-ja-colab
wav2vec2-large-xls-r-300m-ja-colab is a automatic speech recognition model from pinot. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
343
Public
Repo size
6.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Aug 22, 2022
- Updated
- Aug 26, 2022
- SHA
- c603264d
Datasets
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. -->
wav2vec2-large-xls-r-300m-ja-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_10_0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.1407
- Wer: 0.2456
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 637 | 5.3238 | 0.9663 |
| No log | 2.0 | 1274 | 4.1785 | 0.7662 |
| No log | 3.0 | 1911 | 2.3701 | 0.4983 |
| No log | 4.0 | 2548 | 1.8443 | 0.4090 |
| 6.5781 | 5.0 | 3185 | 1.4892 | 0.3363 |
| 6.5781 | 6.0 | 3822 | 1.3229 | 0.2995 |
| 6.5781 | 7.0 | 4459 | 1.2418 | 0.2814 |
| 6.5781 | 8.0 | 5096 | 1.1928 | 0.2647 |
| 1.0184 | 9.0 | 5733 | 1.1584 | 0.2520 |
| 1.0184 | 10.0 | 6370 | 1.1407 | 0.2456 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.10.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Aug 22, 2022
- Updated
- Aug 26, 2022