Downloads · 30 days
2
0% of all-time downloads
wav2vec2-xsl-r-300m-hinglish-model
RahulYadav/wav2vec2-xsl-r-300m-hinglish-model
wav2vec2-xsl-r-300m-hinglish-model is a automatic speech recognition model from RahulYadav. 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
445
Public
Repo size
42.9 GB
Likes
1
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
- May 25, 2023
- Updated
- May 26, 2023
- SHA
- 94e9bc54
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-xsl-r-300m-hinglish-model
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 53.3109
- Wer: 1.0
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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 53.5422 | 2.0 | 2 | 54.4465 | 1.0 |
| 52.8519 | 4.0 | 4 | 54.4457 | 1.0 |
| 52.7079 | 6.0 | 6 | 54.4429 | 1.0 |
| 52.9959 | 8.0 | 8 | 54.4348 | 1.0 |
| 53.5864 | 10.0 | 10 | 54.4155 | 1.0 |
| 54.2708 | 12.0 | 12 | 54.3822 | 1.0 |
| 52.6333 | 14.0 | 14 | 54.3357 | 1.0 |
| 55.1505 | 16.0 | 16 | 54.2576 | 1.0 |
| 53.6833 | 18.0 | 18 | 54.2131 | 1.0 |
| 62.8162 | 20.0 | 20 | 54.1127 | 1.0 |
| 54.0794 | 22.0 | 22 | 53.9824 | 1.0 |
| 52.5195 | 24.0 | 24 | 53.8243 | 1.0 |
| 51.6922 | 26.0 | 26 | 53.6767 | 1.0 |
| 51.0235 | 28.0 | 28 | 53.5179 | 1.0 |
| 51.0729 | 30.0 | 30 | 53.3109 | 1.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- May 25, 2023
- Updated
- May 26, 2023