Hugging Face's logo

Ansu
/
whisper-tiny-basque

TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
Ansu commited on
Commit
2683d4d
·
verified ·
1 Parent(s): 271263c

Model save

Browse files
Files changed (2) hide show
  1. README.md +22 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3235
21
- - Wer: 22.3867
22
 
23
  ## Model description
24
 
@@ -51,26 +51,26 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|
54
- | 0.5126 | 0.33 | 500 | 0.6979 | 53.3533 |
55
- | 0.3117 | 0.66 | 1000 | 0.5084 | 37.0488 |
56
- | 0.2552 | 0.99 | 1500 | 0.4231 | 30.1736 |
57
- | 0.2102 | 1.32 | 2000 | 0.3911 | 29.4055 |
58
- | 0.1925 | 1.65 | 2500 | 0.3738 | 26.7079 |
59
- | 0.1767 | 1.98 | 3000 | 0.3588 | 24.9469 |
60
- | 0.1572 | 2.31 | 3500 | 0.3541 | 25.3466 |
61
- | 0.1503 | 2.64 | 4000 | 0.3432 | 24.1726 |
62
- | 0.1485 | 2.97 | 4500 | 0.3347 | 22.8987 |
63
- | 0.131 | 3.3 | 5000 | 0.3336 | 23.1173 |
64
- | 0.1294 | 3.63 | 5500 | 0.3305 | 23.2422 |
65
- | 0.1287 | 3.96 | 6000 | 0.3292 | 22.6240 |
66
- | 0.1153 | 4.29 | 6500 | 0.3270 | 22.5990 |
67
- | 0.1176 | 4.62 | 7000 | 0.3243 | 23.8167 |
68
- | 0.1153 | 4.95 | 7500 | 0.3262 | 22.7051 |
69
- | 0.1093 | 5.28 | 8000 | 0.3248 | 23.8479 |
70
- | 0.1129 | 5.61 | 8500 | 0.3244 | 23.7480 |
71
- | 0.107 | 5.94 | 9000 | 0.3233 | 22.4054 |
72
- | 0.1029 | 6.27 | 9500 | 0.3236 | 22.7801 |
73
- | 0.1056 | 6.61 | 10000 | 0.3235 | 22.3867 |
74
 
75
 
76
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3232
21
+ - Wer: 22.4241
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|
54
+ | 0.5114 | 0.33 | 500 | 0.6930 | 52.5228 |
55
+ | 0.3117 | 0.66 | 1000 | 0.5082 | 37.1487 |
56
+ | 0.2552 | 0.99 | 1500 | 0.4230 | 30.2610 |
57
+ | 0.2102 | 1.32 | 2000 | 0.3911 | 28.6062 |
58
+ | 0.1925 | 1.65 | 2500 | 0.3733 | 26.7453 |
59
+ | 0.1768 | 1.98 | 3000 | 0.3585 | 24.9657 |
60
+ | 0.1572 | 2.31 | 3500 | 0.3539 | 25.3466 |
61
+ | 0.1503 | 2.64 | 4000 | 0.3429 | 24.1913 |
62
+ | 0.1485 | 2.97 | 4500 | 0.3344 | 22.9050 |
63
+ | 0.131 | 3.3 | 5000 | 0.3335 | 22.9799 |
64
+ | 0.1294 | 3.63 | 5500 | 0.3303 | 23.1797 |
65
+ | 0.1287 | 3.96 | 6000 | 0.3290 | 23.0736 |
66
+ | 0.1153 | 4.29 | 6500 | 0.3267 | 22.0619 |
67
+ | 0.1176 | 4.62 | 7000 | 0.3241 | 24.1164 |
68
+ | 0.1153 | 4.95 | 7500 | 0.3260 | 23.9603 |
69
+ | 0.1093 | 5.28 | 8000 | 0.3247 | 23.8541 |
70
+ | 0.1129 | 5.61 | 8500 | 0.3242 | 22.8488 |
71
+ | 0.1069 | 5.94 | 9000 | 0.3231 | 22.4116 |
72
+ | 0.1029 | 6.27 | 9500 | 0.3233 | 22.5678 |
73
+ | 0.1056 | 6.61 | 10000 | 0.3232 | 22.4241 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8690bddc8c4ba24d4e846220f28afc827038ef1420bc22f9b133a53ddaa22faf
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ee5f7d55bd3fee19a22667882824a331662c4ef962900689e02b5c66222a24
3
  size 151061672