Training Ended
Browse files- README.md +78 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Strange18/wav2vec2-nepali-asr
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-nepali-asr
|
| 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 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/prashant-bista-18-thapathali-campus/Nepali%20ASR/runs/df5ce6bo)
|
| 16 |
+
# wav2vec2-nepali-asr
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Strange18/wav2vec2-nepali-asr](https://huggingface.co/Strange18/wav2vec2-nepali-asr) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2388
|
| 21 |
+
- Wer: 0.2797
|
| 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: 1e-05
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: reduce_lr_on_plateau
|
| 48 |
+
- lr_scheduler_warmup_steps: 500
|
| 49 |
+
- num_epochs: 100
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
| 56 |
+
| 0.4862 | 0.7911 | 250 | 0.2694 | 0.2781 |
|
| 57 |
+
| 0.5414 | 1.5823 | 500 | 0.2667 | 0.2773 |
|
| 58 |
+
| 0.5268 | 2.3734 | 750 | 0.2647 | 0.2777 |
|
| 59 |
+
| 0.4893 | 3.1646 | 1000 | 0.2687 | 0.2753 |
|
| 60 |
+
| 0.4744 | 3.9557 | 1250 | 0.2655 | 0.2769 |
|
| 61 |
+
| 0.5347 | 4.7468 | 1500 | 0.2616 | 0.2721 |
|
| 62 |
+
| 0.4838 | 5.5380 | 1750 | 0.2663 | 0.2729 |
|
| 63 |
+
| 0.4995 | 6.3291 | 2000 | 0.2494 | 0.2693 |
|
| 64 |
+
| 0.408 | 7.1203 | 2250 | 0.2555 | 0.2793 |
|
| 65 |
+
| 0.4409 | 7.9114 | 2500 | 0.2510 | 0.2745 |
|
| 66 |
+
| 0.4138 | 8.7025 | 2750 | 0.2456 | 0.2733 |
|
| 67 |
+
| 0.4909 | 9.4937 | 3000 | 0.2462 | 0.2813 |
|
| 68 |
+
| 0.4511 | 10.2848 | 3250 | 0.2419 | 0.2745 |
|
| 69 |
+
| 0.4688 | 11.0759 | 3500 | 0.2439 | 0.2709 |
|
| 70 |
+
| 0.4845 | 11.8671 | 3750 | 0.2388 | 0.2797 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.42.3
|
| 76 |
+
- Pytorch 2.1.2
|
| 77 |
+
- Datasets 2.20.0
|
| 78 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262082180
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea2a459c104b629bb975f43fda839b3dc72d8bced7de8e10ee15ced014f64891
|
| 3 |
size 1262082180
|