Commit
•
9b8e25b
1
Parent(s):
9f8b982
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/speecht5_tts
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: speecht5_finetuned_speaking_style_en
|
| 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 |
+
# speecht5_finetuned_speaking_style_en
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.3277
|
| 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: 8
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 64
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- training_steps: 4000
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.8232 | 0.61 | 100 | 0.5842 |
|
| 54 |
+
| 0.6949 | 1.23 | 200 | 0.4895 |
|
| 55 |
+
| 0.4918 | 1.84 | 300 | 0.3843 |
|
| 56 |
+
| 0.4266 | 2.45 | 400 | 0.3689 |
|
| 57 |
+
| 0.4098 | 3.07 | 500 | 0.3599 |
|
| 58 |
+
| 0.4026 | 3.68 | 600 | 0.3593 |
|
| 59 |
+
| 0.3947 | 4.29 | 700 | 0.3513 |
|
| 60 |
+
| 0.386 | 4.9 | 800 | 0.3481 |
|
| 61 |
+
| 0.3809 | 5.52 | 900 | 0.3457 |
|
| 62 |
+
| 0.3777 | 6.13 | 1000 | 0.3450 |
|
| 63 |
+
| 0.3745 | 6.74 | 1100 | 0.3418 |
|
| 64 |
+
| 0.3724 | 7.36 | 1200 | 0.3409 |
|
| 65 |
+
| 0.3697 | 7.97 | 1300 | 0.3404 |
|
| 66 |
+
| 0.3687 | 8.58 | 1400 | 0.3379 |
|
| 67 |
+
| 0.3684 | 9.2 | 1500 | 0.3373 |
|
| 68 |
+
| 0.3666 | 9.81 | 1600 | 0.3352 |
|
| 69 |
+
| 0.3637 | 10.42 | 1700 | 0.3395 |
|
| 70 |
+
| 0.3638 | 11.03 | 1800 | 0.3333 |
|
| 71 |
+
| 0.3594 | 11.65 | 1900 | 0.3333 |
|
| 72 |
+
| 0.3603 | 12.26 | 2000 | 0.3378 |
|
| 73 |
+
| 0.3592 | 12.87 | 2100 | 0.3316 |
|
| 74 |
+
| 0.3587 | 13.49 | 2200 | 0.3321 |
|
| 75 |
+
| 0.3557 | 14.1 | 2300 | 0.3311 |
|
| 76 |
+
| 0.3568 | 14.71 | 2400 | 0.3300 |
|
| 77 |
+
| 0.3595 | 15.33 | 2500 | 0.3291 |
|
| 78 |
+
| 0.3565 | 15.94 | 2600 | 0.3323 |
|
| 79 |
+
| 0.3549 | 16.55 | 2700 | 0.3305 |
|
| 80 |
+
| 0.3534 | 17.16 | 2800 | 0.3299 |
|
| 81 |
+
| 0.3545 | 17.78 | 2900 | 0.3268 |
|
| 82 |
+
| 0.3533 | 18.39 | 3000 | 0.3298 |
|
| 83 |
+
| 0.3529 | 19.0 | 3100 | 0.3306 |
|
| 84 |
+
| 0.3526 | 19.62 | 3200 | 0.3285 |
|
| 85 |
+
| 0.3513 | 20.23 | 3300 | 0.3274 |
|
| 86 |
+
| 0.3513 | 20.84 | 3400 | 0.3278 |
|
| 87 |
+
| 0.3505 | 21.46 | 3500 | 0.3295 |
|
| 88 |
+
| 0.3502 | 22.07 | 3600 | 0.3283 |
|
| 89 |
+
| 0.3505 | 22.68 | 3700 | 0.3295 |
|
| 90 |
+
| 0.3527 | 23.3 | 3800 | 0.3289 |
|
| 91 |
+
| 0.3518 | 23.91 | 3900 | 0.3275 |
|
| 92 |
+
| 0.3496 | 24.52 | 4000 | 0.3277 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.38.2
|
| 98 |
+
- Pytorch 2.1.2
|
| 99 |
+
- Datasets 2.18.0
|
| 100 |
+
- 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": "4.38.2"
|
| 9 |
+
}
|
runs/Mar13_10-00-59_b5d65499f411/events.out.tfevents.1710324062.b5d65499f411.34.1
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 sha256:6d19d7d01d7361feea141963ef3613b47108e25c478dbe866e33092f013ffad5
|
| 3 |
+
size 25880
|