Commit
•
3650a61
1
Parent(s):
560a92b
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-Urdu
|
| 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-large-xls-r-300m-Urdu
|
| 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: 1.5867
|
| 20 |
+
- Wer: 0.6240
|
| 21 |
+
- Cer: 0.2579
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0003
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 200
|
| 49 |
+
- num_epochs: 100
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 56 |
+
| 11.1231 | 8.31 | 100 | 3.5275 | 1.0 | 1.0 |
|
| 57 |
+
| 3.4028 | 16.63 | 200 | 3.1164 | 1.0 | 1.0 |
|
| 58 |
+
| 3.1973 | 24.94 | 300 | 2.5590 | 1.0 | 1.0 |
|
| 59 |
+
| 1.3774 | 33.31 | 400 | 1.4729 | 0.7646 | 0.3325 |
|
| 60 |
+
| 0.5427 | 41.63 | 500 | 1.4140 | 0.6939 | 0.3001 |
|
| 61 |
+
| 0.3541 | 49.94 | 600 | 1.4532 | 0.6580 | 0.2815 |
|
| 62 |
+
| 0.26 | 58.31 | 700 | 1.5309 | 0.6403 | 0.2726 |
|
| 63 |
+
| 0.2025 | 66.63 | 800 | 1.5230 | 0.6310 | 0.2655 |
|
| 64 |
+
| 0.171 | 74.94 | 900 | 1.5578 | 0.6336 | 0.2632 |
|
| 65 |
+
| 0.1511 | 83.31 | 1000 | 1.5733 | 0.6321 | 0.2635 |
|
| 66 |
+
| 0.1352 | 91.63 | 1100 | 1.6022 | 0.6255 | 0.2608 |
|
| 67 |
+
| 0.1192 | 99.94 | 1200 | 1.5867 | 0.6240 | 0.2579 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.17.0.dev0
|
| 73 |
+
- Pytorch 1.10.2+cu102
|
| 74 |
+
- Datasets 1.18.2.dev0
|
| 75 |
+
- Tokenizers 0.11.0
|