| --- |
| license: apache-2.0 |
| base_model: facebook/wav2vec2-xls-r-300m |
| tags: |
| - generated_from_trainer |
| datasets: |
| - thennal/IMaSC |
| - vrclc/openslr63 |
| - thennal/indic_tts_ml |
| model-index: |
| - name: XLSR-WithLM-Malayalam |
| results: |
| - task: |
| type: automatic-speech-recognition |
| name: Automatic Speech Recognition |
| dataset: |
| name: OpenSLR Malayalam -Test |
| type: vrclc/openslr63 |
| config: ml |
| split: test |
| args: ml |
| metrics: |
| - type: wer |
| value: 27.3 |
| name: WER |
| - task: |
| type: automatic-speech-recognition |
| name: Automatic Speech Recognition |
| dataset: |
| name: Goole Fleurs |
| type: google/fleurs |
| config: ml |
| split: test |
| args: ml |
| metrics: |
| - type: wer |
| value: 37.2 |
| name: WER |
| - task: |
| type: automatic-speech-recognition |
| name: Automatic Speech Recognition |
| dataset: |
| name: MSC |
| type: smcproject/msc |
| config: ml |
| split: train |
| args: ml |
| metrics: |
| - type: wer |
| value: 52.9 |
| name: WER |
|
|
| --- |
| # XLSR-LM-NewData |
|
|
| This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the [IMASC](https://huggingface.co/datasets/thennal/IMaSC), [MSC](https://huggingface.co/datasets/smcproject/MSC), [OpenSLR Malayalam Train split](https://huggingface.co/datasets/vrclc/openslr63) datasets. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1395 |
| - Wer: 0.2952 |
|
|
| ## 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: 0.00024 |
| - 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 |
|
|
