ymoslem
/

whisper-small-ga2en-v3.1

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

ymoslem commited on Apr 26

Commit

953825b

•

1 Parent(s): f249ee2

Update README.md

Files changed (1) hide show

README.md +15 -15

README.md CHANGED Viewed

@@ -40,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
 # Whisper Small GA-EN Speech Translation
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.1870
-- Bleu: 27.57
-- Chrf: 46.72
-- Wer: 70.6439
 ## Model description
@@ -97,16 +97,16 @@ The following hyperparameters were used during training:
 | 0.4354        | 1.18  | 1800 | 23.63 | 45.16 | 1.1621          | 86.1324  |
 | 0.4709        | 1.25  | 1900 | 27.86 | 47.3  | 1.1544          | 73.7506  |
 | 0.4802        | 1.31  | 2000 | 30.25 | 48.12 | 1.1571          | 64.9707  |
-| 0.4565        | 1.38  | 2100 | 1.2095| 24.75 | 44.7            | 77.4426  |
-| 0.4797        | 1.44  | 2200 | 1.2051| 28.46 | 46.03           | 67.1769  |
-| 0.423         | 1.51  | 2300 | 1.2079| 28.34 | 47.65           | 68.6177  |
-| 0.4254        | 1.58  | 2400 | 1.2251| 27.78 | 46.01           | 67.8523  |
-| 0.4493        | 1.64  | 2500 | 1.1898| 26.61 | 47.8            | 71.1391  |
-| 0.3614        | 1.71  | 2600 | 1.2079| 30.08 | 47.25           | 64.2954  |
-| 0.4052        | 1.77  | 2700 | 1.1975| 30.88 | 47.44           | 64.2053  |
-| 0.3541        | 1.84  | 2800 | 1.2006| 28.4  | 46.02           | 70.2837  |
-| 0.3736        | 1.9   | 2900 | 1.1906| 30.82 | 47.52           | 64.1153  |
-| 0.3326        | 1.97  | 3000 | 1.1870| 27.57 | 46.72           | 70.6439  |
 ### Framework versions

 # Whisper Small GA-EN Speech Translation
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset.
+The best model checkpoint (this version) based on ChrF is at step 2500, epoch 1.64, and it achieves the following results on the evaluation set:
+- Loss: 1.1898
+- Bleu: 26.61
+- Chrf: 47.8
+- Wer: 71.1391
 ## Model description
 | 0.4354        | 1.18  | 1800 | 23.63 | 45.16 | 1.1621          | 86.1324  |
 | 0.4709        | 1.25  | 1900 | 27.86 | 47.3  | 1.1544          | 73.7506  |
 | 0.4802        | 1.31  | 2000 | 30.25 | 48.12 | 1.1571          | 64.9707  |
+| 0.4565        | 1.38  | 2100 | 24.75 | 44.7  | 1.2095          | 77.4426  |
+| 0.4797        | 1.44  | 2200 | 28.46 | 46.03 | 1.2051          | 67.1769  |
+| 0.423         | 1.51  | 2300 | 28.34 | 47.65 | 1.2079          | 68.6177  |
+| 0.4254        | 1.58  | 2400 | 27.78 | 46.01 | 1.2251          | 67.8523  |
+| 0.4493        | 1.64  | 2500 | 26.61 | 47.8  | 1.1898          | 71.1391  |
+| 0.3614        | 1.71  | 2600 | 30.08 | 47.25 | 1.2079          | 64.2954  |
+| 0.4052        | 1.77  | 2700 | 30.88 | 47.44 | 1.1975          | 64.2053  |
+| 0.3541        | 1.84  | 2800 | 28.4  | 46.02 | 1.2006          | 70.2837  |
+| 0.3736        | 1.9   | 2900 | 30.82 | 47.52 | 1.1906          | 64.1153  |
+| 0.3326        | 1.97  | 3000 | 27.57 | 46.72 | 1.1870          | 70.6439  |
 ### Framework versions