update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,91 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice_6_1
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-large-mms-1b-odia
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: common_voice_6_1
|
| 17 |
+
type: common_voice_6_1
|
| 18 |
+
config: or
|
| 19 |
+
split: test
|
| 20 |
+
args: or
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 1.0526315789473684
|
| 25 |
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# wav2vec2-large-mms-1b-odia
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_6_1 dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2591
|
| 35 |
+
- Wer: 1.0526
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 0.001
|
| 55 |
+
- train_batch_size: 12
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- lr_scheduler_warmup_steps: 100
|
| 61 |
+
- num_epochs: 4
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 67 |
+
| 20.1037 | 0.23 | 10 | 20.9125 | 1.0 |
|
| 68 |
+
| 17.8006 | 0.45 | 20 | 15.9823 | 1.0 |
|
| 69 |
+
| 12.0829 | 0.68 | 30 | 9.3068 | 1.0 |
|
| 70 |
+
| 5.2122 | 0.91 | 40 | 3.6577 | 1.0012 |
|
| 71 |
+
| 2.8945 | 1.14 | 50 | 1.9252 | 1.2448 |
|
| 72 |
+
| 1.2442 | 1.36 | 60 | 0.7219 | 1.0220 |
|
| 73 |
+
| 0.5149 | 1.59 | 70 | 0.3858 | 1.0122 |
|
| 74 |
+
| 0.3685 | 1.82 | 80 | 0.3202 | 1.0147 |
|
| 75 |
+
| 0.3529 | 2.05 | 90 | 0.3093 | 1.0147 |
|
| 76 |
+
| 0.2863 | 2.27 | 100 | 0.3130 | 1.0135 |
|
| 77 |
+
| 0.2643 | 2.5 | 110 | 0.3145 | 1.0098 |
|
| 78 |
+
| 0.2518 | 2.73 | 120 | 0.2861 | 1.0588 |
|
| 79 |
+
| 0.2783 | 2.95 | 130 | 0.2668 | 1.0649 |
|
| 80 |
+
| 0.2586 | 3.18 | 140 | 0.2714 | 1.0355 |
|
| 81 |
+
| 0.243 | 3.41 | 150 | 0.2631 | 1.0453 |
|
| 82 |
+
| 0.2261 | 3.64 | 160 | 0.2642 | 1.0367 |
|
| 83 |
+
| 0.2365 | 3.86 | 170 | 0.2591 | 1.0526 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.31.0.dev0
|
| 89 |
+
- Pytorch 2.0.1+cu117
|
| 90 |
+
- Datasets 2.12.0
|
| 91 |
+
- Tokenizers 0.13.3
|