End of training
Browse files- README.md +81 -0
- generation_config.json +9 -0
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/speecht5_tts
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- mozilla-foundation/common_voice_13_0
|
| 8 |
+
model-index:
|
| 9 |
+
- name: speecht5_pt_full
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# speecht5_pt_full
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the mozilla-foundation/common_voice_13_0 dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5021
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 1e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 300
|
| 48 |
+
- training_steps: 2000
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 0.8882 | 0.18 | 100 | 0.7494 |
|
| 55 |
+
| 0.7726 | 0.36 | 200 | 0.6657 |
|
| 56 |
+
| 0.642 | 0.54 | 300 | 0.5767 |
|
| 57 |
+
| 0.6042 | 0.71 | 400 | 0.5545 |
|
| 58 |
+
| 0.5972 | 0.89 | 500 | 0.5342 |
|
| 59 |
+
| 0.5832 | 1.07 | 600 | 0.5337 |
|
| 60 |
+
| 0.5851 | 1.25 | 700 | 0.5291 |
|
| 61 |
+
| 0.5744 | 1.43 | 800 | 0.5245 |
|
| 62 |
+
| 0.5638 | 1.61 | 900 | 0.5186 |
|
| 63 |
+
| 0.5562 | 1.78 | 1000 | 0.5174 |
|
| 64 |
+
| 0.56 | 1.96 | 1100 | 0.5133 |
|
| 65 |
+
| 0.5446 | 2.14 | 1200 | 0.5113 |
|
| 66 |
+
| 0.5556 | 2.32 | 1300 | 0.5099 |
|
| 67 |
+
| 0.5457 | 2.5 | 1400 | 0.5071 |
|
| 68 |
+
| 0.5504 | 2.68 | 1500 | 0.5087 |
|
| 69 |
+
| 0.5497 | 2.85 | 1600 | 0.5039 |
|
| 70 |
+
| 0.545 | 3.03 | 1700 | 0.5034 |
|
| 71 |
+
| 0.5503 | 3.21 | 1800 | 0.5051 |
|
| 72 |
+
| 0.5621 | 3.39 | 1900 | 0.5040 |
|
| 73 |
+
| 0.5347 | 3.57 | 2000 | 0.5021 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.34.0
|
| 79 |
+
- Pytorch 2.0.1+cu118
|
| 80 |
+
- Datasets 2.14.5
|
| 81 |
+
- Tokenizers 0.14.1
|
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": "4.34.0"
|
| 9 |
+
}
|