Downloads · 30 days
3
1% of all-time downloads
wav2vec2-large-xlsr-53_toy_train_data_fast_10pct
scasutt/wav2vec2-large-xlsr-53_toy_train_data_fast_10pct
wav2vec2-large-xlsr-53_toy_train_data_fast_10pct 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
352
Public
Repo size
12.6 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
- Mar 28, 2022
- Updated
- Mar 28, 2022
- SHA
- 615d71a1
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-xlsr-53_toy_train_data_fast_10pct
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6983
- Wer: 0.5026
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.3619 | 1.05 | 250 | 3.4334 | 1.0 |
| 3.0818 | 2.1 | 500 | 3.4914 | 1.0 |
| 2.3245 | 3.15 | 750 | 1.6483 | 0.9486 |
| 1.0233 | 4.2 | 1000 | 0.8817 | 0.7400 |
| 0.7522 | 5.25 | 1250 | 0.7374 | 0.6529 |
| 0.5343 | 6.3 | 1500 | 0.6972 | 0.6068 |
| 0.4452 | 7.35 | 1750 | 0.6757 | 0.5740 |
| 0.4275 | 8.4 | 2000 | 0.6789 | 0.5551 |
| 0.3688 | 9.45 | 2250 | 0.6468 | 0.5394 |
| 0.3363 | 10.5 | 2500 | 0.6798 | 0.5358 |
| 0.3036 | 11.55 | 2750 | 0.6439 | 0.5265 |
| 0.3173 | 12.6 | 3000 | 0.6898 | 0.5196 |
| 0.2985 | 13.65 | 3250 | 0.6791 | 0.5169 |
| 0.288 | 14.7 | 3500 | 0.6442 | 0.5090 |
| 0.2673 | 15.75 | 3750 | 0.6984 | 0.5119 |
| 0.2575 | 16.81 | 4000 | 0.7146 | 0.5084 |
| 0.239 | 17.86 | 4250 | 0.6847 | 0.5040 |
| 0.2266 | 18.91 | 4500 | 0.6900 | 0.5028 |
| 0.22 | 19.96 | 4750 | 0.6983 | 0.5026 |
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 28, 2022
- Updated
- Mar 28, 2022