Hugging Face's logo

ymoslem
/
whisper-tiny-ga2en-v1.4

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Irish
English
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
ymoslem commited on
Commit
5fd96fb
·
verified ·
1 Parent(s): 0e4db59

End of training

Browse files
Files changed (3) hide show
  1. README.md +26 -2
  2. model.safetensors +1 -1
  3. runs/Apr01_02-12-43_69d0de2105f6/events.out.tfevents.1711937670.69d0de2105f6.496.0 +2 -2
README.md CHANGED
@@ -3,17 +3,25 @@ license: apache-2.0
3
  base_model: openai/whisper-tiny
4
  tags:
5
  - generated_from_trainer
 
 
 
6
  model-index:
7
- - name: whisper-tiny-ga2en-v1.4
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
- # whisper-tiny-ga2en-v1.4
15
 
16
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -42,6 +50,22 @@ The following hyperparameters were used during training:
42
  - training_steps: 1000
43
  - mixed_precision_training: Native AMP
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ### Framework versions
46
 
47
  - Transformers 4.39.2
 
3
  base_model: openai/whisper-tiny
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ - wer
9
  model-index:
10
+ - name: Whisper Tiny GA-EN Speech Translation v.1.4
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # Whisper Tiny GA-EN Speech Translation v.1.4
18
 
19
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.7420
22
+ - Bleu: 14.71
23
+ - Chrf: 30.02
24
+ - Wer: 95.7226
25
 
26
  ## Model description
27
 
 
50
  - training_steps: 1000
51
  - mixed_precision_training: Native AMP
52
 
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Wer |
56
+ |:-------------:|:-----:|:----:|:---------------:|:-----:|:-----:|:--------:|
57
+ | 0.8117 | 1.47 | 100 | 2.1773 | 8.81 | 24.15 | 119.9910 |
58
+ | 0.3555 | 2.94 | 200 | 2.2596 | 11.81 | 27.7 | 110.8510 |
59
+ | 0.0872 | 4.41 | 300 | 2.4108 | 12.89 | 28.57 | 110.5808 |
60
+ | 0.063 | 5.88 | 400 | 2.5306 | 12.67 | 27.78 | 107.1139 |
61
+ | 0.034 | 7.35 | 500 | 2.5784 | 17.0 | 30.42 | 85.8622 |
62
+ | 0.0349 | 8.82 | 600 | 2.6201 | 16.64 | 29.98 | 86.8978 |
63
+ | 0.0198 | 10.29 | 700 | 2.7151 | 16.0 | 30.04 | 88.2936 |
64
+ | 0.0134 | 11.76 | 800 | 2.7159 | 14.16 | 30.03 | 105.0878 |
65
+ | 0.0088 | 13.24 | 900 | 2.7369 | 14.61 | 29.32 | 94.3269 |
66
+ | 0.0056 | 14.71 | 1000 | 2.7420 | 14.71 | 30.02 | 95.7226 |
67
+
68
+
69
  ### Framework versions
70
 
71
  - Transformers 4.39.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaf610556de4d9259fe7fff9bebe94769e3a86ea9bc7c8debf7e1560b306e47d
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33eb2fcb99494617bebb9f82c12a68375f3f821595363b44d22365482cc615b6
3
  size 151061672
runs/Apr01_02-12-43_69d0de2105f6/events.out.tfevents.1711937670.69d0de2105f6.496.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4c9676021c4a503e758e557251b383d396e205cb751e0b2cb047b069975f1ce
3
- size 18025
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3aeb2a2042390298e6505a9dbbdf8c6af407cb7b7dd2d3892d8224ef5bfd0a
3
+ size 18379