metadata

base_model: facebook/w2v-bert-2.0
license: mit
datasets:
  - thennal/IMaSC
  - vrclc/festvox-iiith-ml
  - vrclc/openslr63
  - smcproject/msc
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
tags:
  - generated_from_trainer
model-index:
  - name: w2v2bert-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: 20.37
            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: 39.27
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 16 Malayalam
          type: mozilla-foundation/common_voice_16_1
          config: ml
          split: test
          args: ml
        metrics:
          - type: wer
            value: 53.14
            name: WER

W2V2-BERT-Malayalam

This model is a fine-tuned version of facebook/w2v-bert-2.0 on an these datasets: IMASC, MSC, OpenSLR Malayalam Train split, Festvox Malayalam, common_voice_16_1 It achieves the following results on the evaluation set:

Loss: 0.1722
Wer: 0.1299

Training procedure

Trained on NVIDIA A100 GPU

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.1416	0.46	600	0.3393	0.4616
0.1734	0.92	1200	0.2414	0.3493
0.1254	1.38	1800	0.2205	0.2963
0.1097	1.84	2400	0.2157	0.3133
0.0923	2.3	3000	0.1854	0.2473
0.0792	2.76	3600	0.1939	0.2471
0.0696	3.22	4200	0.1720	0.2282
0.0589	3.68	4800	0.1768	0.2013
0.0552	4.14	5400	0.1635	0.1864
0.0437	4.6	6000	0.1501	0.1826
0.0408	5.06	6600	0.1500	0.1645
0.0314	5.52	7200	0.1559	0.1655
0.0317	5.98	7800	0.1448	0.1553
0.022	6.44	8400	0.1592	0.1590
0.0218	6.9	9000	0.1431	0.1458
0.0154	7.36	9600	0.1514	0.1366
0.0141	7.82	10200	0.1540	0.1383
0.0113	8.28	10800	0.1558	0.1391
0.0085	8.74	11400	0.1612	0.1356
0.0072	9.2	12000	0.1697	0.1289
0.0046	9.66	12600	0.1722	0.1299

Framework versions

Transformers 4.39.3
Pytorch 2.1.1+cu121
Datasets 2.16.1
Tokenizers 0.15.1