Update README.md
Browse files
README.md
CHANGED
|
@@ -6,9 +6,16 @@ tags:
|
|
| 6 |
metrics:
|
| 7 |
- bleu
|
| 8 |
- wer
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: Whisper Base GA-EN Speech Translation
|
| 11 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
# Whisper Base GA-EN Speech Translation
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
| 20 |
-
|
| 21 |
- Loss: 2.2482
|
| 22 |
- Bleu: 20.8
|
| 23 |
- Chrf: 35.56
|
|
@@ -71,4 +78,4 @@ The following hyperparameters were used during training:
|
|
| 71 |
- Transformers 4.39.2
|
| 72 |
- Pytorch 2.2.1+cu121
|
| 73 |
- Datasets 2.18.0
|
| 74 |
-
- Tokenizers 0.15.2
|
|
|
|
| 6 |
metrics:
|
| 7 |
- bleu
|
| 8 |
- wer
|
| 9 |
+
- chrf
|
| 10 |
model-index:
|
| 11 |
- name: Whisper Base GA-EN Speech Translation
|
| 12 |
results: []
|
| 13 |
+
datasets:
|
| 14 |
+
- ymoslem/IWSLT2023-GA-EN
|
| 15 |
+
language:
|
| 16 |
+
- ga
|
| 17 |
+
- en
|
| 18 |
+
library_name: transformers
|
| 19 |
---
|
| 20 |
|
| 21 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 24 |
# Whisper Base GA-EN Speech Translation
|
| 25 |
|
| 26 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
| 27 |
+
The best model based on ChrF (this version) is at checkpoint 1000, epoch 3.72, and it achieves the following results on the evaluation set:
|
| 28 |
- Loss: 2.2482
|
| 29 |
- Bleu: 20.8
|
| 30 |
- Chrf: 35.56
|
|
|
|
| 78 |
- Transformers 4.39.2
|
| 79 |
- Pytorch 2.2.1+cu121
|
| 80 |
- Datasets 2.18.0
|
| 81 |
+
- Tokenizers 0.15.2
|