update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2_common_voice_accents_indian
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2_common_voice_accents_indian
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2692
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0003
|
| 39 |
+
- train_batch_size: 48
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- total_train_batch_size: 384
|
| 45 |
+
- total_eval_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 500
|
| 49 |
+
- num_epochs: 30
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 4.5186 | 1.28 | 400 | 0.6937 |
|
| 57 |
+
| 0.3485 | 2.56 | 800 | 0.2323 |
|
| 58 |
+
| 0.2229 | 3.83 | 1200 | 0.2195 |
|
| 59 |
+
| 0.1877 | 5.11 | 1600 | 0.2147 |
|
| 60 |
+
| 0.1618 | 6.39 | 2000 | 0.2058 |
|
| 61 |
+
| 0.1434 | 7.67 | 2400 | 0.2077 |
|
| 62 |
+
| 0.132 | 8.95 | 2800 | 0.1995 |
|
| 63 |
+
| 0.1223 | 10.22 | 3200 | 0.2146 |
|
| 64 |
+
| 0.1153 | 11.5 | 3600 | 0.2117 |
|
| 65 |
+
| 0.1061 | 12.78 | 4000 | 0.2071 |
|
| 66 |
+
| 0.1003 | 14.06 | 4400 | 0.2219 |
|
| 67 |
+
| 0.0949 | 15.34 | 4800 | 0.2204 |
|
| 68 |
+
| 0.0889 | 16.61 | 5200 | 0.2162 |
|
| 69 |
+
| 0.0824 | 17.89 | 5600 | 0.2243 |
|
| 70 |
+
| 0.0784 | 19.17 | 6000 | 0.2323 |
|
| 71 |
+
| 0.0702 | 20.45 | 6400 | 0.2325 |
|
| 72 |
+
| 0.0665 | 21.73 | 6800 | 0.2334 |
|
| 73 |
+
| 0.0626 | 23.0 | 7200 | 0.2411 |
|
| 74 |
+
| 0.058 | 24.28 | 7600 | 0.2473 |
|
| 75 |
+
| 0.054 | 25.56 | 8000 | 0.2591 |
|
| 76 |
+
| 0.0506 | 26.84 | 8400 | 0.2577 |
|
| 77 |
+
| 0.0484 | 28.12 | 8800 | 0.2633 |
|
| 78 |
+
| 0.0453 | 29.39 | 9200 | 0.2692 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.17.0
|
| 84 |
+
- Pytorch 1.10.2+cu102
|
| 85 |
+
- Datasets 1.18.4
|
| 86 |
+
- Tokenizers 0.11.6
|