End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: miosipof/speecht5_tts_voxpopuli_it_v2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- audiofolder
|
| 8 |
+
model-index:
|
| 9 |
+
- name: speecht5_tts_dysarthria_v1
|
| 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_tts_dysarthria_v1
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [miosipof/speecht5_tts_voxpopuli_it_v2](https://huggingface.co/miosipof/speecht5_tts_voxpopuli_it_v2) on the audiofolder dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5234
|
| 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: 5e-06
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 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: 100
|
| 48 |
+
- training_steps: 500
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 55 |
+
| 1.0113 | 0.7042 | 25 | 0.8442 |
|
| 56 |
+
| 0.8 | 1.4085 | 50 | 0.7084 |
|
| 57 |
+
| 0.7291 | 2.1127 | 75 | 0.6323 |
|
| 58 |
+
| 0.6698 | 2.8169 | 100 | 0.5875 |
|
| 59 |
+
| 0.6339 | 3.5211 | 125 | 0.5633 |
|
| 60 |
+
| 0.5747 | 4.2254 | 150 | 0.5552 |
|
| 61 |
+
| 0.5837 | 4.9296 | 175 | 0.5436 |
|
| 62 |
+
| 0.5882 | 5.6338 | 200 | 0.5417 |
|
| 63 |
+
| 0.5692 | 6.3380 | 225 | 0.5363 |
|
| 64 |
+
| 0.5577 | 7.0423 | 250 | 0.5340 |
|
| 65 |
+
| 0.5411 | 7.7465 | 275 | 0.5323 |
|
| 66 |
+
| 0.5551 | 8.4507 | 300 | 0.5301 |
|
| 67 |
+
| 0.5671 | 9.1549 | 325 | 0.5292 |
|
| 68 |
+
| 0.5313 | 9.8592 | 350 | 0.5254 |
|
| 69 |
+
| 0.5546 | 10.5634 | 375 | 0.5246 |
|
| 70 |
+
| 0.5283 | 11.2676 | 400 | 0.5231 |
|
| 71 |
+
| 0.5484 | 11.9718 | 425 | 0.5222 |
|
| 72 |
+
| 0.5251 | 12.6761 | 450 | 0.5222 |
|
| 73 |
+
| 0.5443 | 13.3803 | 475 | 0.5223 |
|
| 74 |
+
| 0.5357 | 14.0845 | 500 | 0.5234 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.43.3
|
| 80 |
+
- Pytorch 2.5.0+cu124
|
| 81 |
+
- Datasets 3.0.1
|
| 82 |
+
- Tokenizers 0.19.1
|
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": "4.43.3"
|
| 9 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 577789320
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2952016d8eecbc0b7a0864a9a4a1f726a143704991636f3fe7ba840b8affd545
|
| 3 |
size 577789320
|
runs/Oct26_18-38-07_13ad67d29fbd/events.out.tfevents.1729967890.13ad67d29fbd
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 sha256:9c2d182eabe7853a44482600a566753371b9ef4d11e18b2416f9ca910cea97ab
|
| 3 |
+
size 16506
|