rinabuoy/whisper-tiny-khmer-aug
Browse files- README.md +21 -8
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: openai/whisper-tiny
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: whisper-tiny-khmer-aug
|
| 8 |
results: []
|
|
@@ -15,13 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
-
|
| 19 |
-
-
|
| 20 |
-
- eval_runtime: 549.3345
|
| 21 |
-
- eval_samples_per_second: 1.809
|
| 22 |
-
- eval_steps_per_second: 0.115
|
| 23 |
-
- epoch: 2.0
|
| 24 |
-
- step: 1340
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -51,9 +48,25 @@ The following hyperparameters were used during training:
|
|
| 51 |
- lr_scheduler_warmup_steps: 1000
|
| 52 |
- num_epochs: 10
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.44.0
|
| 57 |
-
- Pytorch 2.3.1
|
| 58 |
- Datasets 2.21.0
|
| 59 |
- Tokenizers 0.19.1
|
|
|
|
| 3 |
base_model: openai/whisper-tiny
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
model-index:
|
| 9 |
- name: whisper-tiny-khmer-aug
|
| 10 |
results: []
|
|
|
|
| 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: 0.2697
|
| 21 |
+
- Wer: 68.1206
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 48 |
- lr_scheduler_warmup_steps: 1000
|
| 49 |
- num_epochs: 10
|
| 50 |
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 55 |
+
| 0.8969 | 1.0 | 670 | 0.4289 | 91.3572 |
|
| 56 |
+
| 0.3822 | 2.0 | 1340 | 0.3025 | 79.3741 |
|
| 57 |
+
| 0.292 | 3.0 | 2010 | 0.2727 | 85.6819 |
|
| 58 |
+
| 0.2439 | 4.0 | 2680 | 0.2637 | 74.1365 |
|
| 59 |
+
| 0.2124 | 5.0 | 3350 | 0.2548 | 70.2124 |
|
| 60 |
+
| 0.1844 | 6.0 | 4020 | 0.2606 | 79.7470 |
|
| 61 |
+
| 0.1651 | 7.0 | 4690 | 0.2505 | 68.5909 |
|
| 62 |
+
| 0.1472 | 8.0 | 5360 | 0.2637 | 67.9261 |
|
| 63 |
+
| 0.1344 | 9.0 | 6030 | 0.2672 | 66.2234 |
|
| 64 |
+
| 0.1194 | 10.0 | 6700 | 0.2697 | 68.1206 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
- Transformers 4.44.0
|
| 70 |
+
- Pytorch 2.3.1
|
| 71 |
- Datasets 2.21.0
|
| 72 |
- Tokenizers 0.19.1
|
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 sha256:2f7db0fe9b70ec3923e504f628e0a530474dd40f25551ab697372a62cfa1948c
|
| 3 |
size 151061672
|