End of training
Browse files- README.md +24 -10
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,19 +1,23 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
datasets:
|
| 5 |
- audiofolder
|
| 6 |
model-index:
|
| 7 |
-
- name:
|
| 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 |
-
#
|
| 15 |
|
| 16 |
-
This model
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -32,25 +36,35 @@ More information needed
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
-
- learning_rate:
|
| 36 |
- train_batch_size: 32
|
| 37 |
-
- eval_batch_size:
|
| 38 |
- seed: 42
|
| 39 |
-
- gradient_accumulation_steps:
|
| 40 |
-
- total_train_batch_size:
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- lr_scheduler_warmup_steps:
|
| 44 |
-
- num_epochs:
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- Transformers 4.43.3
|
| 54 |
-
- Pytorch 2.4.
|
| 55 |
- Datasets 3.0.1
|
| 56 |
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/speecht5_vc
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- audiofolder
|
| 8 |
model-index:
|
| 9 |
+
- name: SpeechT5_finetuned_kha
|
| 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_finetuned_kha
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [microsoft/speecht5_vc](https://huggingface.co/microsoft/speecht5_vc) on the audiofolder dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4733
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 16
|
| 44 |
+
- total_train_batch_size: 512
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 1000
|
| 48 |
+
- num_epochs: 300
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:--------:|:----:|:---------------:|
|
| 55 |
+
| 0.544 | 36.8664 | 1000 | 0.5145 |
|
| 56 |
+
| 0.5013 | 73.7327 | 2000 | 0.4800 |
|
| 57 |
+
| 0.4754 | 110.5991 | 3000 | 0.4705 |
|
| 58 |
+
| 0.4651 | 147.4654 | 4000 | 0.4710 |
|
| 59 |
+
| 0.456 | 184.3318 | 5000 | 0.4699 |
|
| 60 |
+
| 0.446 | 221.1982 | 6000 | 0.4702 |
|
| 61 |
+
| 0.443 | 258.0645 | 7000 | 0.4714 |
|
| 62 |
+
| 0.4437 | 294.9309 | 8000 | 0.4733 |
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
- Transformers 4.43.3
|
| 68 |
+
- Pytorch 2.4.0
|
| 69 |
- Datasets 3.0.1
|
| 70 |
- Tokenizers 0.19.1
|
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:d46a33bc7aecf68c3addb88992fcef5ff8c10f90b508b4eca37dcbc7fb3fbc37
|
| 3 |
size 577789320
|