End of training
Browse files
README.md
CHANGED
@@ -1,19 +1,48 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: openai/whisper-medium
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
-
- name:
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
-
#
|
15 |
|
16 |
-
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -42,6 +71,32 @@ The following hyperparameters were used during training:
|
|
42 |
- training_steps: 2000
|
43 |
- mixed_precision_training: Native AMP
|
44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
### Framework versions
|
46 |
|
47 |
- Transformers 4.41.2
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- ga
|
4 |
+
- en
|
5 |
license: apache-2.0
|
6 |
base_model: openai/whisper-medium
|
7 |
tags:
|
8 |
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- ymoslem/IWSLT2023-GA-EN
|
11 |
+
- ymoslem/FLEURS-GA-EN
|
12 |
+
- ymoslem/BitesizeIrish-GA-EN
|
13 |
+
- ymoslem/SpokenWords-GA-EN-MTed
|
14 |
+
metrics:
|
15 |
+
- bleu
|
16 |
+
- wer
|
17 |
model-index:
|
18 |
+
- name: Whisper Medium GA-EN Speech Translation Raw + warmup_ratio=0.01
|
19 |
+
results:
|
20 |
+
- task:
|
21 |
+
name: Automatic Speech Recognition
|
22 |
+
type: automatic-speech-recognition
|
23 |
+
dataset:
|
24 |
+
name: IWSLT-2023, FLEURS, BiteSize, and SpokenWords
|
25 |
+
type: ymoslem/IWSLT2023-GA-EN
|
26 |
+
metrics:
|
27 |
+
- name: Bleu
|
28 |
+
type: bleu
|
29 |
+
value: 30.23
|
30 |
+
- name: Wer
|
31 |
+
type: wer
|
32 |
+
value: 65.37595677622693
|
33 |
---
|
34 |
|
35 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
36 |
should probably proofread and complete it, then remove this comment. -->
|
37 |
|
38 |
+
# Whisper Medium GA-EN Speech Translation Raw + warmup_ratio=0.01
|
39 |
|
40 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the IWSLT-2023, FLEURS, BiteSize, and SpokenWords dataset.
|
41 |
+
It achieves the following results on the evaluation set:
|
42 |
+
- Loss: 1.4321
|
43 |
+
- Bleu: 30.23
|
44 |
+
- Chrf: 48.18
|
45 |
+
- Wer: 65.3760
|
46 |
|
47 |
## Model description
|
48 |
|
|
|
71 |
- training_steps: 2000
|
72 |
- mixed_precision_training: Native AMP
|
73 |
|
74 |
+
### Training results
|
75 |
+
|
76 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Wer |
|
77 |
+
|:-------------:|:------:|:----:|:---------------:|:-----:|:-----:|:--------:|
|
78 |
+
| 2.6013 | 0.0539 | 100 | 2.2401 | 3.18 | 17.57 | 139.4417 |
|
79 |
+
| 2.5749 | 0.1079 | 200 | 3.0398 | 0.0 | 3.87 | 100.4052 |
|
80 |
+
| 2.3449 | 0.1618 | 300 | 2.0560 | 7.53 | 24.09 | 121.0266 |
|
81 |
+
| 2.0392 | 0.2157 | 400 | 1.9721 | 10.7 | 29.63 | 109.7253 |
|
82 |
+
| 1.9155 | 0.2697 | 500 | 1.9402 | 16.73 | 31.59 | 81.9901 |
|
83 |
+
| 1.9148 | 0.3236 | 600 | 1.7868 | 11.12 | 32.9 | 117.1544 |
|
84 |
+
| 1.698 | 0.3776 | 700 | 1.7244 | 20.14 | 36.31 | 83.8811 |
|
85 |
+
| 1.7283 | 0.4315 | 800 | 1.6586 | 16.74 | 34.0 | 94.5070 |
|
86 |
+
| 1.5213 | 0.4854 | 900 | 1.6387 | 19.49 | 38.29 | 84.2413 |
|
87 |
+
| 1.3123 | 0.5394 | 1000 | 1.6292 | 22.27 | 41.45 | 80.2792 |
|
88 |
+
| 1.1584 | 0.5933 | 1100 | 1.5900 | 25.48 | 42.03 | 74.2008 |
|
89 |
+
| 1.1734 | 0.6472 | 1200 | 1.5495 | 17.77 | 40.1 | 106.9338 |
|
90 |
+
| 1.2271 | 0.7012 | 1300 | 1.4978 | 21.7 | 43.63 | 84.2413 |
|
91 |
+
| 1.0872 | 0.7551 | 1400 | 1.4690 | 25.34 | 43.98 | 74.2909 |
|
92 |
+
| 0.9331 | 0.8091 | 1500 | 1.4688 | 20.09 | 43.14 | 90.5448 |
|
93 |
+
| 0.7861 | 0.8630 | 1600 | 1.4284 | 26.49 | 46.76 | 76.4971 |
|
94 |
+
| 0.8392 | 0.9169 | 1700 | 1.3909 | 27.22 | 46.91 | 73.3904 |
|
95 |
+
| 0.7236 | 0.9709 | 1800 | 1.4349 | 26.98 | 46.01 | 74.2008 |
|
96 |
+
| 0.2741 | 1.0248 | 1900 | 1.4279 | 28.92 | 47.63 | 68.3476 |
|
97 |
+
| 0.2782 | 1.0787 | 2000 | 1.4321 | 30.23 | 48.18 | 65.3760 |
|
98 |
+
|
99 |
+
|
100 |
### Framework versions
|
101 |
|
102 |
- Transformers 4.41.2
|