End of training
Browse files
README.md
CHANGED
|
@@ -17,7 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [fahadqazi/speecht5_sindhi](https://huggingface.co/fahadqazi/speecht5_sindhi) on the fleurs dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -36,7 +41,7 @@ More information needed
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
-
- learning_rate:
|
| 40 |
- train_batch_size: 8
|
| 41 |
- eval_batch_size: 2
|
| 42 |
- seed: 42
|
|
@@ -48,22 +53,6 @@ The following hyperparameters were used during training:
|
|
| 48 |
- training_steps: 1000
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
-
| 1.2419 | 0.8264 | 100 | 1.1933 |
|
| 56 |
-
| 1.2074 | 1.6529 | 200 | 1.1755 |
|
| 57 |
-
| 1.1745 | 2.4793 | 300 | 1.1743 |
|
| 58 |
-
| 1.1925 | 3.3058 | 400 | 1.2545 |
|
| 59 |
-
| 1.1739 | 4.1322 | 500 | 1.1852 |
|
| 60 |
-
| 1.185 | 4.9587 | 600 | 1.2277 |
|
| 61 |
-
| 1.1687 | 5.7851 | 700 | 1.2069 |
|
| 62 |
-
| 1.2063 | 6.6116 | 800 | 1.1875 |
|
| 63 |
-
| 1.1456 | 7.4380 | 900 | 1.1866 |
|
| 64 |
-
| 1.1672 | 8.2645 | 1000 | 1.1844 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
- Transformers 4.44.2
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [fahadqazi/speecht5_sindhi](https://huggingface.co/fahadqazi/speecht5_sindhi) on the fleurs dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- eval_loss: 1.1110
|
| 21 |
+
- eval_runtime: 14.4754
|
| 22 |
+
- eval_samples_per_second: 19.205
|
| 23 |
+
- eval_steps_per_second: 9.603
|
| 24 |
+
- epoch: 6.3898
|
| 25 |
+
- step: 500
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 5e-05
|
| 45 |
- train_batch_size: 8
|
| 46 |
- eval_batch_size: 2
|
| 47 |
- seed: 42
|
|
|
|
| 53 |
- training_steps: 1000
|
| 54 |
- mixed_precision_training: Native AMP
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
- Transformers 4.44.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 577930632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:689b8dcb6b1fbe22e5622caafb02dac044cc4cabce457de5c33992d300ef7eda
|
| 3 |
size 577930632
|
runs/Nov03_09-22-21_ae69d7103884/events.out.tfevents.1730625752.ae69d7103884.3198.2
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 sha256:58282083b840766d6644c03940f5c7bf193e2822f4634d520a92f5b2e717d9c3
|
| 3 |
+
size 12509
|