Downloads · 30 days
11
3% of all-time downloads
wav2vec2-large-xlsr-53_full_train_full_train
scasutt/wav2vec2-large-xlsr-53_full_train_full_train
wav2vec2-large-xlsr-53_full_train_full_train is a automatic speech recognition model from scasutt. 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
370
Public
Repo size
24 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
- Model type
- wav2vec2
- Access
- Public
- Created
- May 13, 2022
- Updated
- May 16, 2022
- SHA
- 0db21014
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_full_train_full_train
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8369
- Wer: 0.5052
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.533 | 1.35 | 1000 | 0.3547 | 0.3483 |
| 0.4531 | 2.69 | 2000 | 0.8369 | 0.5052 |
Framework versions
- Transformers 4.19.0
- Pytorch 1.11.0+cu102
- Datasets 2.2.1
- Tokenizers 0.12.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- May 13, 2022
- Updated
- May 16, 2022