Hugging Face's logo

neddamj
/
whisper-tiny-patois

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
neddamj commited on
Commit
5a01f36
·
verified ·
1 Parent(s): a04ba13

End of training

Browse files
Files changed (4) hide show
  1. README.md +13 -13
  2. model.safetensors +1 -1
  3. runs/May29_19-05-00_5da1fcbbbf12/events.out.tfevents.1748545502.5da1fcbbbf12.4065.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Wer
25
  type: wer
26
- value: 0.7472737952345685
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Patois Music Transcription dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 1.3223
37
- - Wer: 0.7473
38
 
39
  ## Model description
40
 
@@ -67,16 +67,16 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-------:|:----:|:---------------:|:------:|
70
- | 1.7475 | 1.8100 | 400 | 1.7326 | 1.1959 |
71
- | 1.17 | 3.6199 | 800 | 1.3909 | 0.9394 |
72
- | 0.9114 | 5.4299 | 1200 | 1.2935 | 0.8480 |
73
- | 0.6738 | 7.2398 | 1600 | 1.2597 | 0.8131 |
74
- | 0.539 | 9.0498 | 2000 | 1.2475 | 0.7652 |
75
- | 0.4953 | 10.8597 | 2400 | 1.2574 | 0.7642 |
76
- | 0.4019 | 12.6697 | 2800 | 1.2778 | 0.7585 |
77
- | 0.3587 | 14.4796 | 3200 | 1.2999 | 0.7584 |
78
- | 0.3056 | 16.2896 | 3600 | 1.3150 | 0.7520 |
79
- | 0.2939 | 18.0995 | 4000 | 1.3223 | 0.7473 |
80
 
81
 
82
  ### Framework versions
 
23
  metrics:
24
  - name: Wer
25
  type: wer
26
+ value: 0.8005095879112787
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Patois Music Transcription dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.6927
37
+ - Wer: 0.8005
38
 
39
  ## Model description
40
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-------:|:----:|:---------------:|:------:|
70
+ | 1.6981 | 2.6490 | 400 | 1.7500 | 1.2964 |
71
+ | 1.0133 | 5.2980 | 800 | 1.4418 | 0.9557 |
72
+ | 0.7521 | 7.9470 | 1200 | 1.3821 | 0.8719 |
73
+ | 0.5125 | 10.5960 | 1600 | 1.4081 | 0.7962 |
74
+ | 0.3403 | 13.2450 | 2000 | 1.4613 | 0.8105 |
75
+ | 0.2737 | 15.8940 | 2400 | 1.5187 | 0.7902 |
76
+ | 0.1871 | 18.5430 | 2800 | 1.5868 | 0.7868 |
77
+ | 0.146 | 21.1921 | 3200 | 1.6405 | 0.7881 |
78
+ | 0.13 | 23.8411 | 3600 | 1.6760 | 0.8007 |
79
+ | 0.1154 | 26.4901 | 4000 | 1.6927 | 0.8005 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca4570fcc64a11f818af61b0a7e6af191d06143db28a2528bd341e05d292b3a5
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f40d2814b519c963d5a3a3775f268ce06b273225cf47252ca890ee649ddb8a1
3
  size 151061672
runs/May29_19-05-00_5da1fcbbbf12/events.out.tfevents.1748545502.5da1fcbbbf12.4065.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959894a394c74494c2b37d94997a73e2be8bf45cdcb8aca2bdc7111a8c7d04c4
3
+ size 43947
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbe5c3548e3da150d43aa7af505438a0319812729f6022261825da2b5b70190d
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adcc48d3da73d5fdf74de50d044d9e0116d961a016bb398679ea8282bc7b0e64
3
  size 5432