End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/speecht5_tts
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: malay_dataset_checkpoint
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# malay_dataset_checkpoint
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.5938
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 3
|
| 39 |
+
- eval_batch_size: 3
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 3.0
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 1.8835 | 0.17 | 500 | 1.1947 |
|
| 50 |
+
| 1.156 | 0.34 | 1000 | 0.9847 |
|
| 51 |
+
| 1.0174 | 0.51 | 1500 | 0.8688 |
|
| 52 |
+
| 0.9117 | 0.68 | 2000 | 0.7840 |
|
| 53 |
+
| 0.8413 | 0.86 | 2500 | 0.7218 |
|
| 54 |
+
| 0.8081 | 1.03 | 3000 | 0.7093 |
|
| 55 |
+
| 0.7662 | 1.2 | 3500 | 0.6677 |
|
| 56 |
+
| 0.746 | 1.37 | 4000 | 0.6525 |
|
| 57 |
+
| 0.7318 | 1.54 | 4500 | 0.6492 |
|
| 58 |
+
| 0.7043 | 1.71 | 5000 | 0.6472 |
|
| 59 |
+
| 0.7157 | 1.88 | 5500 | 0.6153 |
|
| 60 |
+
| 0.6821 | 2.05 | 6000 | 0.6070 |
|
| 61 |
+
| 0.692 | 2.23 | 6500 | 0.6133 |
|
| 62 |
+
| 0.671 | 2.4 | 7000 | 0.6089 |
|
| 63 |
+
| 0.6676 | 2.57 | 7500 | 0.6000 |
|
| 64 |
+
| 0.6769 | 2.74 | 8000 | 0.5956 |
|
| 65 |
+
| 0.6612 | 2.91 | 8500 | 0.5938 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.40.0.dev0
|
| 71 |
+
- Pytorch 2.2.1+cu121
|
| 72 |
+
- Datasets 2.18.0
|
| 73 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"max_length": 1876,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.40.0.dev0"
|
| 9 |
+
}
|
runs/Apr02_11-16-40_4cd0e96387f9/events.out.tfevents.1712056601.4cd0e96387f9.3636.0
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:a927791f4f578beb0976d82843ffc9161769f0f0bbb4390d61f76db637dc276c
|
| 3 |
+
size 14911
|