End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: dawid511/speecht5_finetuned_librispeech_polish_epo6_batch8_gas4
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: speecht5_finetuned_librispeech_polish_epo10_batch2_gas2
|
| 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_librispeech_polish_epo10_batch2_gas2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [dawid511/speecht5_finetuned_librispeech_polish_epo6_batch8_gas4](https://huggingface.co/dawid511/speecht5_finetuned_librispeech_polish_epo6_batch8_gas4) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.3637
|
| 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: 0.0001
|
| 38 |
+
- train_batch_size: 2
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 4
|
| 43 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 100
|
| 46 |
+
- num_epochs: 10
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 0.7279 | 0.2558 | 100 | 0.3734 |
|
| 54 |
+
| 0.7647 | 0.5115 | 200 | 0.3829 |
|
| 55 |
+
| 0.7646 | 0.7673 | 300 | 0.3793 |
|
| 56 |
+
| 0.7521 | 1.0230 | 400 | 0.3804 |
|
| 57 |
+
| 0.7673 | 1.2788 | 500 | 0.3817 |
|
| 58 |
+
| 0.7415 | 1.5345 | 600 | 0.3824 |
|
| 59 |
+
| 0.7721 | 1.7903 | 700 | 0.3960 |
|
| 60 |
+
| 0.7766 | 2.0460 | 800 | 0.3767 |
|
| 61 |
+
| 0.7529 | 2.3018 | 900 | 0.3756 |
|
| 62 |
+
| 0.757 | 2.5575 | 1000 | 0.3809 |
|
| 63 |
+
| 0.757 | 2.8133 | 1100 | 0.3808 |
|
| 64 |
+
| 0.746 | 3.0691 | 1200 | 0.3762 |
|
| 65 |
+
| 0.7424 | 3.3248 | 1300 | 0.3744 |
|
| 66 |
+
| 0.7409 | 3.5806 | 1400 | 0.3778 |
|
| 67 |
+
| 0.7453 | 3.8363 | 1500 | 0.3715 |
|
| 68 |
+
| 0.7409 | 4.0921 | 1600 | 0.3722 |
|
| 69 |
+
| 0.7441 | 4.3478 | 1700 | 0.3728 |
|
| 70 |
+
| 0.7304 | 4.6036 | 1800 | 0.3724 |
|
| 71 |
+
| 0.738 | 4.8593 | 1900 | 0.3710 |
|
| 72 |
+
| 0.7213 | 5.1151 | 2000 | 0.3730 |
|
| 73 |
+
| 0.7446 | 5.3708 | 2100 | 0.3721 |
|
| 74 |
+
| 0.7255 | 5.6266 | 2200 | 0.3684 |
|
| 75 |
+
| 0.7321 | 5.8824 | 2300 | 0.3671 |
|
| 76 |
+
| 0.7098 | 6.1381 | 2400 | 0.3673 |
|
| 77 |
+
| 0.7401 | 6.3939 | 2500 | 0.3735 |
|
| 78 |
+
| 0.7165 | 6.6496 | 2600 | 0.3679 |
|
| 79 |
+
| 0.714 | 6.9054 | 2700 | 0.3733 |
|
| 80 |
+
| 0.7035 | 7.1611 | 2800 | 0.3666 |
|
| 81 |
+
| 0.7089 | 7.4169 | 2900 | 0.3689 |
|
| 82 |
+
| 0.7118 | 7.6726 | 3000 | 0.3691 |
|
| 83 |
+
| 0.7064 | 7.9284 | 3100 | 0.3664 |
|
| 84 |
+
| 0.6994 | 8.1841 | 3200 | 0.3679 |
|
| 85 |
+
| 0.6958 | 8.4399 | 3300 | 0.3661 |
|
| 86 |
+
| 0.7087 | 8.6957 | 3400 | 0.3683 |
|
| 87 |
+
| 0.6968 | 8.9514 | 3500 | 0.3635 |
|
| 88 |
+
| 0.7035 | 9.2072 | 3600 | 0.3647 |
|
| 89 |
+
| 0.7045 | 9.4629 | 3700 | 0.3647 |
|
| 90 |
+
| 0.6982 | 9.7187 | 3800 | 0.3642 |
|
| 91 |
+
| 0.6996 | 9.9744 | 3900 | 0.3637 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- Transformers 4.47.1
|
| 97 |
+
- Pytorch 2.5.1+cu121
|
| 98 |
+
- Datasets 3.2.0
|
| 99 |
+
- Tokenizers 0.21.0
|
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 |
+
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.47.1",
|
| 8 |
+
"use_cache": false
|
| 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:f428efbb94135d0a8383b3b65123aed4e64ef4f2df0c5ef1f19ef6277e867e35
|
| 3 |
size 577789320
|
runs/Jan10_16-55-43_d31b3f597294/events.out.tfevents.1736528147.d31b3f597294.1037.8
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:c447f0087f2edfd46bd1cac610ea83183458d6324efc9ea56454284573c66660
|
| 3 |
+
size 50644
|