Downloads · 30 days
6
2% of all-time downloads
wav2vec2-large-xls-r-300m-euskera2.1-colab
KatMarie/wav2vec2-large-xls-r-300m-euskera2.1-colab
wav2vec2-large-xls-r-300m-euskera2.1-colab is a automatic speech recognition model from KatMarie. 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
342
Public
Repo size
46.7 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 17, 2023
- Updated
- Sep 1, 2023
- SHA
- 3f81a894
Base models
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-euskera2.1-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.2291
- Wer: 0.2787
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: 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: 500
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.1152 | 1.49 | 700 | 0.3510 | 0.4973 |
| 0.1969 | 2.98 | 1400 | 0.2552 | 0.3643 |
| 0.1027 | 4.47 | 2100 | 0.2379 | 0.3108 |
| 0.0648 | 5.96 | 2800 | 0.2291 | 0.2787 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Aug 17, 2023
- Updated
- Sep 1, 2023