End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- nl
|
| 5 |
+
license: mit
|
| 6 |
+
base_model: microsoft/speecht5_tts
|
| 7 |
+
tags:
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- procit007/saskia_may23_39768
|
| 11 |
+
model-index:
|
| 12 |
+
- name: speecht5_tts_v1_100
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# speecht5_tts_v1_100
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the saskia_may23_39768 dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.4580
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 1e-05
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 2
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 8
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 500
|
| 51 |
+
- num_epochs: 90
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-------:|:-----:|:---------------:|
|
| 57 |
+
| 0.5267 | 2.7939 | 1000 | 0.4852 |
|
| 58 |
+
| 0.4925 | 5.5870 | 2000 | 0.4635 |
|
| 59 |
+
| 0.488 | 8.3802 | 3000 | 0.4534 |
|
| 60 |
+
| 0.4771 | 11.1733 | 4000 | 0.4528 |
|
| 61 |
+
| 0.4703 | 13.9672 | 5000 | 0.4473 |
|
| 62 |
+
| 0.4566 | 16.7603 | 6000 | 0.4435 |
|
| 63 |
+
| 0.4548 | 19.5535 | 7000 | 0.4532 |
|
| 64 |
+
| 0.4499 | 22.3466 | 8000 | 0.4473 |
|
| 65 |
+
| 0.456 | 25.1398 | 9000 | 0.4446 |
|
| 66 |
+
| 0.4531 | 27.9336 | 10000 | 0.4457 |
|
| 67 |
+
| 0.4479 | 30.7268 | 11000 | 0.4495 |
|
| 68 |
+
| 0.4461 | 33.5199 | 12000 | 0.4430 |
|
| 69 |
+
| 0.4384 | 36.3131 | 13000 | 0.4410 |
|
| 70 |
+
| 0.4346 | 39.1062 | 14000 | 0.4475 |
|
| 71 |
+
| 0.4399 | 41.9001 | 15000 | 0.4461 |
|
| 72 |
+
| 0.4342 | 44.6932 | 16000 | 0.4455 |
|
| 73 |
+
| 0.433 | 47.4864 | 17000 | 0.4486 |
|
| 74 |
+
| 0.4344 | 50.2795 | 18000 | 0.4568 |
|
| 75 |
+
| 0.433 | 53.0727 | 19000 | 0.4490 |
|
| 76 |
+
| 0.4318 | 55.8665 | 20000 | 0.4554 |
|
| 77 |
+
| 0.4292 | 58.6597 | 21000 | 0.4535 |
|
| 78 |
+
| 0.4289 | 61.4528 | 22000 | 0.4510 |
|
| 79 |
+
| 0.4284 | 64.2460 | 23000 | 0.4534 |
|
| 80 |
+
| 0.43 | 67.0391 | 24000 | 0.4489 |
|
| 81 |
+
| 0.4277 | 69.8330 | 25000 | 0.4541 |
|
| 82 |
+
| 0.429 | 72.6261 | 26000 | 0.4548 |
|
| 83 |
+
| 0.423 | 75.4193 | 27000 | 0.4612 |
|
| 84 |
+
| 0.4265 | 78.2124 | 28000 | 0.4516 |
|
| 85 |
+
| 0.4344 | 81.0056 | 29000 | 0.4584 |
|
| 86 |
+
| 0.4303 | 83.7994 | 30000 | 0.4610 |
|
| 87 |
+
| 0.4279 | 86.5926 | 31000 | 0.4562 |
|
| 88 |
+
| 0.428 | 89.3857 | 32000 | 0.4580 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Framework versions
|
| 92 |
+
|
| 93 |
+
- Transformers 4.56.0.dev0
|
| 94 |
+
- Pytorch 2.6.0+cu124
|
| 95 |
+
- Datasets 3.6.0
|
| 96 |
+
- Tokenizers 0.21.2
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
2
|
| 7 |
+
],
|
| 8 |
+
"max_length": 1876,
|
| 9 |
+
"pad_token_id": 1,
|
| 10 |
+
"transformers_version": "4.56.0.dev0"
|
| 11 |
+
}
|
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 sha256:6a40e4de634d381177c9de2d120ce6080ee038388592d43d74c5e5739d85f903
|
| 3 |
size 577789320
|
runs/Aug22_16-19-47_240c73c9d929/events.out.tfevents.1755879592.240c73c9d929.36.1
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:cc4607bf106cc9a3edb0ce4441b92420333718166fb6d29e4741d31f919b8d83
|
| 3 |
+
size 289945
|