Hugging Face's logo

Baselhany
/
Whisper_tiny_tring_large_sample_with_early_stop2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
Baselhany commited on
Commit
30e0c7d
·
verified ·
1 Parent(s): 6903c93

Training finished

Browse files
Files changed (3) hide show
  1. README.md +10 -15
  2. model.safetensors +1 -1
  3. runs/Feb01_12-45-23_3a56d515a42d/events.out.tfevents.1738429128.3a56d515a42d.18.1 +3 -0
README.md CHANGED
@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0075
24
- - Wer: 0.1302
25
- - Cer: 0.0524
26
 
27
  ## Model description
28
 
@@ -57,18 +57,13 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0068 | 1.0 | 313 | 0.0074 | 0.1296 | 0.0499 |
61
- | 0.0069 | 2.0 | 626 | 0.0074 | 0.1283 | 0.0462 |
62
- | 0.0065 | 3.0 | 939 | 0.0074 | 0.1256 | 0.0446 |
63
- | 0.0047 | 4.0 | 1252 | 0.0072 | 0.1285 | 0.0451 |
64
- | 0.0043 | 5.0 | 1565 | 0.0072 | 0.1211 | 0.0428 |
65
- | 0.0042 | 6.0 | 1878 | 0.0073 | 0.1256 | 0.0470 |
66
- | 0.0033 | 7.0 | 2191 | 0.0074 | 0.1307 | 0.0473 |
67
- | 0.0036 | 8.0 | 2504 | 0.0075 | 0.1312 | 0.0481 |
68
- | 0.0034 | 9.0 | 2817 | 0.0076 | 0.1303 | 0.0485 |
69
- | 0.0024 | 10.0 | 3130 | 0.0078 | 0.1287 | 0.0470 |
70
- | 0.0026 | 11.0 | 3443 | 0.0078 | 0.1283 | 0.0466 |
71
- | 0.0019 | 12.0 | 3756 | 0.0079 | 0.1290 | 0.0464 |
72
 
73
 
74
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0081
24
+ - Wer: 0.1274
25
+ - Cer: 0.0518
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.003 | 1.0 | 313 | 0.0074 | 0.1301 | 0.0465 |
61
+ | 0.0037 | 2.0 | 626 | 0.0075 | 0.1319 | 0.0481 |
62
+ | 0.0036 | 3.0 | 939 | 0.0075 | 0.1309 | 0.0487 |
63
+ | 0.0027 | 4.0 | 1252 | 0.0077 | 0.1213 | 0.0419 |
64
+ | 0.0025 | 5.0 | 1565 | 0.0079 | 0.1381 | 0.0642 |
65
+ | 0.0022 | 6.0 | 1878 | 0.0080 | 0.1310 | 0.0486 |
66
+ | 0.0018 | 7.0 | 2191 | 0.0082 | 0.1252 | 0.0472 |
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2095f930bb8b6661e64030cbe5b25c0975c69ad70e023079090f6b1a5a0e2880
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816eb46deaea6c1d6eb2e5597bb4b1b83d8bf309a758a520197d24e82ef8ddb5
3
  size 151061672
runs/Feb01_12-45-23_3a56d515a42d/events.out.tfevents.1738429128.3a56d515a42d.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052a3e61116e8b0e7c03d05a61a83d75b5bae72aafafb02fe774cefa4bde8998
3
+ size 453