weekcircle
/

wav2vec2-large-mms-1b-korean-colab_v2

@@ -1,6 +1,6 @@
 ---
 license: cc-by-nc-4.0
-base_model: weekcircle/wav2vec2-large-mms-1b-korean-colab
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-large-mms-1b-korean-colab_v2
-This model is a fine-tuned version of [weekcircle/wav2vec2-large-mms-1b-korean-colab](https://huggingface.co/weekcircle/wav2vec2-large-mms-1b-korean-colab) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1086
-- Wer: 0.2620
 ## Model description
@@ -37,47 +37,35 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 7.4685        | 0.18  | 100  | 0.2959          | 0.5194 |
-| 0.2803        | 0.36  | 200  | 0.1893          | 0.3906 |
-| 0.2519        | 0.53  | 300  | 0.1935          | 0.3878 |
-| 0.242         | 0.71  | 400  | 0.1732          | 0.3789 |
-| 0.2402        | 0.89  | 500  | 0.1626          | 0.3585 |
-| 0.2176        | 1.07  | 600  | 0.1512          | 0.3382 |
-| 0.2036        | 1.24  | 700  | 0.1619          | 0.3644 |
-| 0.21          | 1.42  | 800  | 0.1434          | 0.3348 |
-| 0.2035        | 1.6   | 900  | 0.1477          | 0.3357 |
-| 0.2091        | 1.78  | 1000 | 0.1376          | 0.3064 |
-| 0.1876        | 1.95  | 1100 | 0.1383          | 0.3194 |
-| 0.177         | 2.13  | 1200 | 0.1367          | 0.3076 |
-| 0.174         | 2.31  | 1300 | 0.1347          | 0.3086 |
-| 0.1816        | 2.49  | 1400 | 0.1317          | 0.3138 |
-| 0.1885        | 2.66  | 1500 | 0.1252          | 0.3009 |
-| 0.1703        | 2.84  | 1600 | 0.1268          | 0.3006 |
-| 0.1751        | 3.02  | 1700 | 0.1245          | 0.3030 |
-| 0.1635        | 3.2   | 1800 | 0.1225          | 0.2895 |
-| 0.1582        | 3.37  | 1900 | 0.1188          | 0.2864 |
-| 0.1522        | 3.55  | 2000 | 0.1164          | 0.2777 |
-| 0.1579        | 3.73  | 2100 | 0.1171          | 0.2839 |
-| 0.1489        | 3.91  | 2200 | 0.1175          | 0.2700 |
-| 0.1465        | 4.09  | 2300 | 0.1124          | 0.2682 |
-| 0.1339        | 4.26  | 2400 | 0.1153          | 0.2759 |
-| 0.1427        | 4.44  | 2500 | 0.1125          | 0.2694 |
-| 0.1466        | 4.62  | 2600 | 0.1105          | 0.2639 |
-| 0.1421        | 4.8   | 2700 | 0.1101          | 0.2608 |
-| 0.1466        | 4.97  | 2800 | 0.1086          | 0.2620 |
 ### Framework versions

 ---
 license: cc-by-nc-4.0
+base_model: facebook/mms-1b-l1107
 tags:
 - generated_from_trainer
 metrics:
 # wav2vec2-large-mms-1b-korean-colab_v2
+This model is a fine-tuned version of [facebook/mms-1b-l1107](https://huggingface.co/facebook/mms-1b-l1107) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1650
+- Wer: 0.3776
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.005
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
+- num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 4.6667        | 0.18  | 100  | 0.8024          | 0.8379 |
+| 0.5754        | 0.36  | 200  | 0.3907          | 0.6495 |
+| 0.4658        | 0.53  | 300  | 0.3620          | 0.6224 |
+| 0.4321        | 0.71  | 400  | 0.3184          | 0.5842 |
+| 0.399         | 0.89  | 500  | 0.2930          | 0.5120 |
+| 0.3538        | 1.07  | 600  | 0.2446          | 0.4698 |
+| 0.3379        | 1.24  | 700  | 0.2341          | 0.4692 |
+| 0.3333        | 1.42  | 800  | 0.2121          | 0.4488 |
+| 0.31          | 1.6   | 900  | 0.2054          | 0.4297 |
+| 0.3049        | 1.78  | 1000 | 0.1958          | 0.4180 |
+| 0.2885        | 1.95  | 1100 | 0.1885          | 0.4143 |
+| 0.2632        | 2.13  | 1200 | 0.1865          | 0.4094 |
+| 0.2592        | 2.31  | 1300 | 0.1774          | 0.3853 |
+| 0.2591        | 2.49  | 1400 | 0.1700          | 0.3924 |
+| 0.2605        | 2.66  | 1500 | 0.1701          | 0.3789 |
+| 0.2361        | 2.84  | 1600 | 0.1650          | 0.3776 |
 ### Framework versions