Downloads · 30 days
13
3% of all-time downloads
XLSR-WithLM-Malayalam
kavyamanohar/XLSR-WithLM-Malayalam
XLSR-WithLM-Malayalam is a automatic speech recognition model from kavyamanohar. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the IMASC, Indic TTS Malayalam, OpenSLR Malayalam Train split datasets.
All-time downloads
495
Public
Parameters
316M
1.4 GB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 93%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jul 22, 2024
- Updated
- Jul 23, 2024
- SHA
- a6de0ae6
Base models
Model card
From the Hugging Face model README
XLSR-WithLM-Malayalam
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the IMASC, Indic TTS Malayalam, OpenSLR Malayalam Train split datasets. It achieves the following results on the evaluation set:
- Loss: 0.1395
- Wer: 0.2952
Trigram Language Model Trained using KENLM Library on kavyamanohar/ml-sentences dataset
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.00024
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 800
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.4912 | 0.1165 | 1000 | 0.5497 | 0.7011 |
| 0.5377 | 0.2330 | 2000 | 0.3292 | 0.5364 |
| 0.4343 | 0.3494 | 3000 | 0.2475 | 0.4424 |
| 0.3678 | 0.4659 | 4000 | 0.2145 | 0.4014 |
| 0.3345 | 0.5824 | 5000 | 0.1898 | 0.3774 |
| 0.3029 | 0.6989 | 6000 | 0.1718 | 0.3441 |
| 0.2685 | 0.8153 | 7000 | 0.1517 | 0.3135 |
| 0.2385 | 0.9318 | 8000 | 0.1395 | 0.2952 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jul 22, 2024
- Updated
- Jul 23, 2024