Downloads · 30 days
6
2% of all-time downloads
swadeshi_bhojpuriwav2vec2asr
pritam18/swadeshi_bhojpuriwav2vec2asr
swadeshi_bhojpuriwav2vec2asr is a automatic speech recognition model from pritam18. 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
384
Public
Repo size
3.8 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
- May 25, 2022
- Updated
- May 25, 2022
- SHA
- c7dc0df5
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. -->
swadeshi_bhojpuriwav2vec2asr
This model is a fine-tuned version of theainerd/Wav2Vec2-large-xlsr-hindi on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2155
- Wer: 0.2931
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: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.6928 | 3.2 | 400 | 2.4820 | 0.9925 |
| 1.6981 | 6.4 | 800 | 0.8053 | 0.6320 |
| 0.975 | 9.6 | 1200 | 0.5420 | 0.4980 |
| 0.7672 | 12.8 | 1600 | 0.4224 | 0.4233 |
| 0.636 | 16.0 | 2000 | 0.3481 | 0.3774 |
| 0.5562 | 19.2 | 2400 | 0.2861 | 0.3409 |
| 0.4973 | 22.4 | 2800 | 0.2450 | 0.3211 |
| 0.4616 | 25.6 | 3200 | 0.2230 | 0.3004 |
| 0.4264 | 28.8 | 3600 | 0.2155 | 0.2931 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.2.3.dev0
- Tokenizers 0.12.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- May 25, 2022
- Updated
- May 25, 2022