Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,7 @@ datasets:
|
|
| 14 |
metrics:
|
| 15 |
- bleu
|
| 16 |
- wer
|
|
|
|
| 17 |
model-index:
|
| 18 |
- name: Whisper Large GA-EN Speech Translation
|
| 19 |
results:
|
|
@@ -39,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 39 |
|
| 40 |
This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset.
|
| 41 |
It achieves the following results on the evaluation set:
|
| 42 |
-
- Loss: 1.
|
| 43 |
-
- Bleu: 31.
|
| 44 |
-
- Chrf: 50.
|
| 45 |
-
- Wer:
|
| 46 |
-
|
| 47 |
## Model description
|
| 48 |
|
| 49 |
More information needed
|
|
@@ -114,4 +115,4 @@ The following hyperparameters were used during training:
|
|
| 114 |
- Transformers 4.40.0
|
| 115 |
- Pytorch 2.0.1+cu118
|
| 116 |
- Datasets 2.18.0
|
| 117 |
-
- Tokenizers 0.19.1
|
|
|
|
| 14 |
metrics:
|
| 15 |
- bleu
|
| 16 |
- wer
|
| 17 |
+
- chrf
|
| 18 |
model-index:
|
| 19 |
- name: Whisper Large GA-EN Speech Translation
|
| 20 |
results:
|
|
|
|
| 40 |
|
| 41 |
This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset.
|
| 42 |
It achieves the following results on the evaluation set:
|
| 43 |
+
- Loss: 1.1318
|
| 44 |
+
- Bleu: 31.26
|
| 45 |
+
- Chrf: 50.41
|
| 46 |
+
- Wer: 62.3143
|
| 47 |
+
|
| 48 |
## Model description
|
| 49 |
|
| 50 |
More information needed
|
|
|
|
| 115 |
- Transformers 4.40.0
|
| 116 |
- Pytorch 2.0.1+cu118
|
| 117 |
- Datasets 2.18.0
|
| 118 |
+
- Tokenizers 0.19.1
|