ymoslem commited on
Commit
45f0038
1 Parent(s): d06e232

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -16
README.md CHANGED
@@ -40,12 +40,13 @@ should probably proofread and complete it, then remove this comment. -->
40
  # Whisper Small GA-EN Speech Translation
41
 
42
  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.
43
- It achieves the following results on the evaluation set:
44
- - Loss: 1.2924
45
- - Bleu: 30.91
46
- - Chrf: 47.99
47
- - Wer: 65.1058
48
-
 
49
  ## Model description
50
 
51
  More information needed
@@ -107,16 +108,16 @@ The following hyperparameters were used during training:
107
  | 0.4047 | 0.6130 | 2800 | 29.9 | 47.79 | 1.2450 | 66.9968 |
108
  | 0.3719 | 0.6349 | 2900 | 30.5 | 48.78 | 1.2522 | 65.1959 |
109
  | 0.327 | 0.6567 | 3000 | 31.22 | 49.0 | 1.2493 | 64.1153 |
110
- | 0.3138 | 0.6786 | 3100 | 1.2653| 30.1 | 47.82 | 65.1959 |
111
- | 0.3349 | 0.7005 | 3200 | 1.2651| 30.37 | 48.64 | 63.9802 |
112
- | 0.2807 | 0.7224 | 3300 | 1.2762| 26.02 | 45.46 | 76.8573 |
113
- | 0.2648 | 0.7443 | 3400 | 1.2761| 30.65 | 47.58 | 64.6105 |
114
- | 0.2633 | 0.7662 | 3500 | 1.2890| 29.73 | 47.74 | 65.5110 |
115
- | 0.2316 | 0.7881 | 3600 | 1.2886| 29.94 | 47.33 | 66.4566 |
116
- | 0.233 | 0.8100 | 3700 | 1.2905| 27.82 | 48.01 | 73.1202 |
117
- | 0.2196 | 0.8319 | 3800 | 1.2994| 31.51 | 48.66 | 63.7100 |
118
- | 0.2119 | 0.8538 | 3900 | 1.2910| 30.09 | 48.44 | 65.0158 |
119
- | 0.2082 | 0.8757 | 4000 | 1.2924| 30.91 | 47.99 | 65.1058 |
120
 
121
 
122
  ### Framework versions
 
40
  # Whisper Small GA-EN Speech Translation
41
 
42
  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.
43
+ The datasets are augmented in two ways: noise augmentation, and truncating low-magnitude samples.
44
+ The best model checkpoint (this version) based on ChrF is at step 2000, epoch 0.4378, and it achieves the following results on the evaluation set:
45
+ - Loss: 1.2119
46
+ - Bleu: 30.93
47
+ - Chrf: 49.09
48
+ - Wer: 63.1247
49
+
50
  ## Model description
51
 
52
  More information needed
 
108
  | 0.4047 | 0.6130 | 2800 | 29.9 | 47.79 | 1.2450 | 66.9968 |
109
  | 0.3719 | 0.6349 | 2900 | 30.5 | 48.78 | 1.2522 | 65.1959 |
110
  | 0.327 | 0.6567 | 3000 | 31.22 | 49.0 | 1.2493 | 64.1153 |
111
+ | 0.3138 | 0.6786 | 3100 | 30.1 | 47.82 | 1.2653 | 65.1959 |
112
+ | 0.3349 | 0.7005 | 3200 | 30.37 | 48.64 | 1.2651 | 63.9802 |
113
+ | 0.2807 | 0.7224 | 3300 | 26.02 | 45.46 | 1.2762 | 76.8573 |
114
+ | 0.2648 | 0.7443 | 3400 | 30.65 | 47.58 | 1.2761 | 64.6105 |
115
+ | 0.2633 | 0.7662 | 3500 | 29.73 | 47.74 | 1.2890 | 65.5110 |
116
+ | 0.2316 | 0.7881 | 3600 | 29.94 | 47.33 | 1.2886 | 66.4566 |
117
+ | 0.233 | 0.8100 | 3700 | 27.82 | 48.01 | 1.2905 | 73.1202 |
118
+ | 0.2196 | 0.8319 | 3800 | 31.51 | 48.66 | 1.2994 | 63.7100 |
119
+ | 0.2119 | 0.8538 | 3900 | 30.09 | 48.44 | 1.2910 | 65.0158 |
120
+ | 0.2082 | 0.8757 | 4000 | 30.91 | 47.99 | 1.2924 | 65.1058 |
121
 
122
 
123
  ### Framework versions