update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- hi
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- mozilla-foundation/common_voice_8_0
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- common_voice
|
| 11 |
+
model-index:
|
| 12 |
+
- name: ''
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
#
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - HI dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.8111
|
| 24 |
+
- Wer: 0.5177
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 7.5e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_steps: 2000
|
| 52 |
+
- num_epochs: 50.0
|
| 53 |
+
- mixed_precision_training: Native AMP
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 59 |
+
| 4.9733 | 2.59 | 500 | 5.0697 | 1.0 |
|
| 60 |
+
| 3.3839 | 5.18 | 1000 | 3.3518 | 1.0 |
|
| 61 |
+
| 2.0596 | 7.77 | 1500 | 1.3992 | 0.7869 |
|
| 62 |
+
| 1.6102 | 10.36 | 2000 | 1.0712 | 0.6754 |
|
| 63 |
+
| 1.4587 | 12.95 | 2500 | 0.9280 | 0.6361 |
|
| 64 |
+
| 1.3667 | 15.54 | 3000 | 0.9281 | 0.6155 |
|
| 65 |
+
| 1.3042 | 18.13 | 3500 | 0.9037 | 0.5921 |
|
| 66 |
+
| 1.2544 | 20.73 | 4000 | 0.8996 | 0.5824 |
|
| 67 |
+
| 1.2274 | 23.32 | 4500 | 0.8934 | 0.5797 |
|
| 68 |
+
| 1.1763 | 25.91 | 5000 | 0.8643 | 0.5760 |
|
| 69 |
+
| 1.149 | 28.5 | 5500 | 0.8251 | 0.5544 |
|
| 70 |
+
| 1.1207 | 31.09 | 6000 | 0.8506 | 0.5527 |
|
| 71 |
+
| 1.091 | 33.68 | 6500 | 0.8370 | 0.5366 |
|
| 72 |
+
| 1.0613 | 36.27 | 7000 | 0.8345 | 0.5352 |
|
| 73 |
+
| 1.0495 | 38.86 | 7500 | 0.8380 | 0.5321 |
|
| 74 |
+
| 1.0345 | 41.45 | 8000 | 0.8285 | 0.5269 |
|
| 75 |
+
| 1.0297 | 44.04 | 8500 | 0.7836 | 0.5141 |
|
| 76 |
+
| 1.027 | 46.63 | 9000 | 0.8120 | 0.5180 |
|
| 77 |
+
| 0.9876 | 49.22 | 9500 | 0.8109 | 0.5188 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.16.0.dev0
|
| 83 |
+
- Pytorch 1.10.1+cu113
|
| 84 |
+
- Datasets 1.18.1.dev0
|
| 85 |
+
- Tokenizers 0.11.0
|