Commit
·
d013a86
1
Parent(s):
9abcf70
hindi_wav2vec2_part_2
Browse files
README.md
CHANGED
|
@@ -1,8 +1,10 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: hindi_wav2vec2
|
| 8 |
results: []
|
|
@@ -13,7 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# hindi_wav2vec2
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -40,11 +45,73 @@ The following hyperparameters were used during training:
|
|
| 40 |
- total_train_batch_size: 32
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- lr_scheduler_warmup_steps:
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
|
| 50 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model: TheAIchemist13/hindi_wav2vec2
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
model-index:
|
| 9 |
- name: hindi_wav2vec2
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# hindi_wav2vec2
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [TheAIchemist13/hindi_wav2vec2](https://huggingface.co/TheAIchemist13/hindi_wav2vec2) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0003
|
| 21 |
+
- Wer: 0.5333
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 45 |
- total_train_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: 100
|
| 49 |
+
- num_epochs: 500
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 55 |
+
| No log | 7.14 | 25 | 1.2980 | 1.4167 |
|
| 56 |
+
| No log | 14.29 | 50 | 0.7841 | 1.2833 |
|
| 57 |
+
| No log | 21.43 | 75 | 0.5604 | 1.05 |
|
| 58 |
+
| No log | 28.57 | 100 | 0.5288 | 1.05 |
|
| 59 |
+
| No log | 35.71 | 125 | 0.2642 | 0.8833 |
|
| 60 |
+
| No log | 42.86 | 150 | 0.3233 | 1.0167 |
|
| 61 |
+
| No log | 50.0 | 175 | 0.5526 | 1.0667 |
|
| 62 |
+
| No log | 57.14 | 200 | 0.1759 | 0.8167 |
|
| 63 |
+
| No log | 64.29 | 225 | 0.1275 | 0.6833 |
|
| 64 |
+
| No log | 71.43 | 250 | 0.1004 | 0.7 |
|
| 65 |
+
| No log | 78.57 | 275 | 0.1294 | 0.75 |
|
| 66 |
+
| No log | 85.71 | 300 | 0.1928 | 0.8333 |
|
| 67 |
+
| No log | 92.86 | 325 | 0.1206 | 0.7167 |
|
| 68 |
+
| No log | 100.0 | 350 | 0.1060 | 0.7 |
|
| 69 |
+
| No log | 107.14 | 375 | 0.0676 | 0.65 |
|
| 70 |
+
| No log | 114.29 | 400 | 0.1803 | 0.8667 |
|
| 71 |
+
| No log | 121.43 | 425 | 0.0502 | 0.6333 |
|
| 72 |
+
| No log | 128.57 | 450 | 0.0978 | 0.6833 |
|
| 73 |
+
| No log | 135.71 | 475 | 0.0817 | 0.6167 |
|
| 74 |
+
| 0.553 | 142.86 | 500 | 0.0695 | 0.6667 |
|
| 75 |
+
| 0.553 | 150.0 | 525 | 0.2449 | 0.8333 |
|
| 76 |
+
| 0.553 | 157.14 | 550 | 0.0407 | 0.6 |
|
| 77 |
+
| 0.553 | 164.29 | 575 | 0.0713 | 0.65 |
|
| 78 |
+
| 0.553 | 171.43 | 600 | 0.0317 | 0.6333 |
|
| 79 |
+
| 0.553 | 178.57 | 625 | 0.0383 | 0.6833 |
|
| 80 |
+
| 0.553 | 185.71 | 650 | 0.0217 | 0.6 |
|
| 81 |
+
| 0.553 | 192.86 | 675 | 0.0087 | 0.5667 |
|
| 82 |
+
| 0.553 | 200.0 | 700 | 0.0270 | 0.6167 |
|
| 83 |
+
| 0.553 | 207.14 | 725 | 0.1069 | 0.7 |
|
| 84 |
+
| 0.553 | 214.29 | 750 | 0.0118 | 0.5833 |
|
| 85 |
+
| 0.553 | 221.43 | 775 | 0.0089 | 0.6 |
|
| 86 |
+
| 0.553 | 228.57 | 800 | 0.0072 | 0.5667 |
|
| 87 |
+
| 0.553 | 235.71 | 825 | 0.0510 | 0.5833 |
|
| 88 |
+
| 0.553 | 242.86 | 850 | 0.0187 | 0.5833 |
|
| 89 |
+
| 0.553 | 250.0 | 875 | 0.0199 | 0.5833 |
|
| 90 |
+
| 0.553 | 257.14 | 900 | 0.0105 | 0.5833 |
|
| 91 |
+
| 0.553 | 264.29 | 925 | 0.0082 | 0.5833 |
|
| 92 |
+
| 0.553 | 271.43 | 950 | 0.0177 | 0.5833 |
|
| 93 |
+
| 0.553 | 278.57 | 975 | 0.0032 | 0.55 |
|
| 94 |
+
| 0.103 | 285.71 | 1000 | 0.0036 | 0.55 |
|
| 95 |
+
| 0.103 | 292.86 | 1025 | 0.0028 | 0.5333 |
|
| 96 |
+
| 0.103 | 300.0 | 1050 | 0.0040 | 0.5667 |
|
| 97 |
+
| 0.103 | 307.14 | 1075 | 0.0416 | 0.5667 |
|
| 98 |
+
| 0.103 | 314.29 | 1100 | 0.0055 | 0.5667 |
|
| 99 |
+
| 0.103 | 321.43 | 1125 | 0.0026 | 0.55 |
|
| 100 |
+
| 0.103 | 328.57 | 1150 | 0.0029 | 0.55 |
|
| 101 |
+
| 0.103 | 335.71 | 1175 | 0.0010 | 0.5333 |
|
| 102 |
+
| 0.103 | 342.86 | 1200 | 0.0036 | 0.55 |
|
| 103 |
+
| 0.103 | 350.0 | 1225 | 0.0013 | 0.55 |
|
| 104 |
+
| 0.103 | 357.14 | 1250 | 0.0010 | 0.5333 |
|
| 105 |
+
| 0.103 | 364.29 | 1275 | 0.0013 | 0.5333 |
|
| 106 |
+
| 0.103 | 371.43 | 1300 | 0.0007 | 0.5333 |
|
| 107 |
+
| 0.103 | 378.57 | 1325 | 0.0006 | 0.5333 |
|
| 108 |
+
| 0.103 | 385.71 | 1350 | 0.0005 | 0.5333 |
|
| 109 |
+
| 0.103 | 392.86 | 1375 | 0.0004 | 0.5333 |
|
| 110 |
+
| 0.103 | 400.0 | 1400 | 0.0004 | 0.5333 |
|
| 111 |
+
| 0.103 | 407.14 | 1425 | 0.0004 | 0.5333 |
|
| 112 |
+
| 0.103 | 414.29 | 1450 | 0.0003 | 0.5333 |
|
| 113 |
+
| 0.103 | 421.43 | 1475 | 0.0003 | 0.5333 |
|
| 114 |
+
| 0.0142 | 428.57 | 1500 | 0.0003 | 0.5333 |
|
| 115 |
|
| 116 |
|
| 117 |
### Framework versions
|