Hugging Face's logo

cantillation
/
whisper-medium-he-teamim-aviv-bavly-without-nikud-test

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hebrew
whisper
hf-asr-leaderboard
Generated from Trainer
Model card Files Metrics Community
cantillation commited on
Commit
827824d
·
verified ·
1 Parent(s): 3e409e4

Training in progress, step 2000

Browse files
Files changed (8) hide show
  1. README.md +30 -1
  2. model.safetensors +1 -1
  3. runs/Feb14_22-51-17_sipl-7542-ct/events.out.tfevents.1707951078.sipl-7542-ct.1177613.3 +2 -2
  4. runs/Feb14_22-58-50_sipl-7542-ct/events.out.tfevents.1707951535.sipl-7542-ct.1185350.0 +3 -0
  5. runs/Feb14_23-00-02_sipl-7542-ct/events.out.tfevents.1707951604.sipl-7542-ct.1185350.1 +3 -0
  6. runs/Feb14_23-02-06_sipl-7542-ct/events.out.tfevents.1707951731.sipl-7542-ct.1186316.0 +3 -0
  7. runs/Feb15_06-05-10_sipl-7542-ct/events.out.tfevents.1707977115.sipl-7542-ct.1319778.0 +3 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -6,6 +6,10 @@ base_model: openai/whisper-medium
6
  tags:
7
  - hf-asr-leaderboard
8
  - generated_from_trainer
 
 
 
 
9
  model-index:
10
  - name: he
11
  results: []
@@ -17,6 +21,20 @@ should probably proofread and complete it, then remove this comment. -->
17
  # he
18
 
19
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -42,9 +60,20 @@ The following hyperparameters were used during training:
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 20
45
- - training_steps: 10000
46
  - mixed_precision_training: Native AMP
47
 
 
 
 
 
 
 
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - Transformers 4.36.2
 
6
  tags:
7
  - hf-asr-leaderboard
8
  - generated_from_trainer
9
+ metrics:
10
+ - precision
11
+ - recall
12
+ - f1
13
  model-index:
14
  - name: he
15
  results: []
 
21
  # he
22
 
23
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 1.1249
26
+ - Precision: 0.2559
27
+ - Recall: 0.2742
28
+ - F1: 0.2642
29
+ - Precision Median: 0.25
30
+ - Recall Median: 0.2727
31
+ - F1 Median: 0.2609
32
+ - Precision Max: 0.4211
33
+ - Recall Max: 0.4706
34
+ - F1 Max: 0.4444
35
+ - Precision Min: 0.0526
36
+ - Recall Min: 0.05
37
+ - F1 Min: 0.0513
38
 
39
  ## Model description
40
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_steps: 20
63
+ - training_steps: 25
64
  - mixed_precision_training: Native AMP
65
 
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Precision Median | Recall Median | F1 Median | Precision Max | Recall Max | F1 Max | Precision Min | Recall Min | F1 Min |
69
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:----------------:|:-------------:|:---------:|:-------------:|:----------:|:------:|:-------------:|:----------:|:------:|
70
+ | No log | 0.0 | 5 | 5.8029 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
71
+ | No log | 0.01 | 10 | 2.9216 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
72
+ | No log | 0.01 | 15 | 2.1863 | 0.0540 | 0.0710 | 0.0609 | 0.0476 | 0.0769 | 0.0541 | 0.2 | 0.2353 | 0.2162 | 0.0 | 0.0 | 0.0 |
73
+ | No log | 0.01 | 20 | 1.1833 | 0.3468 | 0.3692 | 0.3565 | 0.4118 | 0.4286 | 0.4242 | 0.8 | 0.8 | 0.8000 | 0.0 | 0.0 | 0.0 |
74
+ | 3.5014 | 0.01 | 25 | 1.1249 | 0.2559 | 0.2742 | 0.2642 | 0.25 | 0.2727 | 0.2609 | 0.4211 | 0.4706 | 0.4444 | 0.0526 | 0.05 | 0.0513 |
75
+
76
+
77
  ### Framework versions
78
 
79
  - Transformers 4.36.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e5e0d51f4c4c74b2d63e48352b9a4e70f6e3885b81b8182dd047346af69a94a
3
  size 3055671280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f54d42f49d8b09dd8b31b9c978a06fcf8845df57976a09f0a437e88625dc530e
3
  size 3055671280
runs/Feb14_22-51-17_sipl-7542-ct/events.out.tfevents.1707951078.sipl-7542-ct.1177613.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf353ad348cd23a9aef510b3185f2d96afe7de4faffd8539a15ed7b70de461d8
3
- size 4136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a11e54dc1073cb4fad02394880af6bcf9e45ae7bc260731442c5b720d10347
3
+ size 5309
runs/Feb14_22-58-50_sipl-7542-ct/events.out.tfevents.1707951535.sipl-7542-ct.1185350.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e147276004fe3e3dab20aaebfc8cfd811b264fb7b74b9fb751b151d1047c63
3
+ size 4136
runs/Feb14_23-00-02_sipl-7542-ct/events.out.tfevents.1707951604.sipl-7542-ct.1185350.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371f58a6fb69357725132622a4b231f6d1c5c9858b8cdcee6f134dc6777559f3
3
+ size 4136
runs/Feb14_23-02-06_sipl-7542-ct/events.out.tfevents.1707951731.sipl-7542-ct.1186316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9394630085c2583a5d1447049e13e40565d3461a06ba8259fa9e384e116b9d8e
3
+ size 10282
runs/Feb15_06-05-10_sipl-7542-ct/events.out.tfevents.1707977115.sipl-7542-ct.1319778.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9bff1cf65c72f5ffe5cb8b214ed46e7a7c3834633412b5be2e9bf9cf8ac651
3
+ size 21504
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9812ba4cbe334061017bf2f7182ab888b7ae14d0476e12140519cc2574234888
3
  size 4475
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d81e4dee5fa4935124c935ad0735bba7504a6a2a97c04edab02cab35debb0d
3
  size 4475