End of training
Browse files
README.md
CHANGED
@@ -35,7 +35,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Whisper for Igbo 1.0 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss: 3.
|
39 |
- Wer: 97.1429
|
40 |
|
41 |
## Model description
|
@@ -61,18 +61,24 @@ The following hyperparameters were used during training:
|
|
61 |
- seed: 42
|
62 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
63 |
- lr_scheduler_type: linear
|
64 |
-
- lr_scheduler_warmup_steps:
|
65 |
-
- training_steps:
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
72 |
-
| No log |
|
73 |
-
| No log |
|
74 |
-
|
|
75 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
|
77 |
|
78 |
### Framework versions
|
|
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Whisper for Igbo 1.0 dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 3.5994
|
39 |
- Wer: 97.1429
|
40 |
|
41 |
## Model description
|
|
|
61 |
- seed: 42
|
62 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
63 |
- lr_scheduler_type: linear
|
64 |
+
- lr_scheduler_warmup_steps: 10
|
65 |
+
- training_steps: 100
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
72 |
+
| No log | 10.0 | 10 | 3.4658 | 108.5714 |
|
73 |
+
| No log | 20.0 | 20 | 3.5388 | 105.7143 |
|
74 |
+
| 0.0225 | 30.0 | 30 | 3.5858 | 97.1429 |
|
75 |
+
| 0.0225 | 40.0 | 40 | 3.5922 | 97.1429 |
|
76 |
+
| 0.0002 | 50.0 | 50 | 3.5956 | 97.1429 |
|
77 |
+
| 0.0002 | 60.0 | 60 | 3.5987 | 97.1429 |
|
78 |
+
| 0.0002 | 70.0 | 70 | 3.5995 | 97.1429 |
|
79 |
+
| 0.0001 | 80.0 | 80 | 3.6001 | 97.1429 |
|
80 |
+
| 0.0001 | 90.0 | 90 | 3.6014 | 97.1429 |
|
81 |
+
| 0.0001 | 100.0 | 100 | 3.5994 | 97.1429 |
|
82 |
|
83 |
|
84 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151061672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b49768a18977a8360b1731facd12202b521d66a5a2bf5c7f4c414f67165f942
|
3 |
size 151061672
|
runs/Mar20_03-06-48_88d34570d106/events.out.tfevents.1742440027.88d34570d106.240.3
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58c1a7ced3455d5839609f74016d8d11dbc8b5c4c95a1d5bbd65c8540e3e874a
|
3 |
+
size 10185
|