Downloads · 30 days
7
17% of all-time downloads
wav2vec2-base_toy_train_data_augment_0.1.csv
scasutt/wav2vec2-base_toy_train_data_augment_0.1.csv
wav2vec2-base_toy_train_data_augment_0.1.csv is a automatic speech recognition model from scasutt. 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
41
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Mar 25, 2022
- Updated
- Mar 25, 2022
- SHA
- c6dfdd82
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-base_toy_train_data_augment_0.1.csv
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3933
- Wer: 0.9997
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 1000
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.2787 | 0.84 | 200 | 3.5920 | 1.0 |
| 3.0613 | 1.68 | 400 | 3.4069 | 1.0 |
| 3.0481 | 2.52 | 600 | 3.4811 | 1.0 |
| 2.896 | 3.36 | 800 | 2.3933 | 0.9997 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.11.0+cu102
- Datasets 2.0.0
- Tokenizers 0.11.6
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Mar 25, 2022
- Updated
- Mar 25, 2022