---
library_name: transformers
base_model: syvai/tts-v1-pretrained
tags:
- axolotl
- generated_from_trainer
datasets:
- syvai/zac-coral-tts
- syvai/zac-dk-voice-pro
- syvai/zac-dk-voice-single-speaker
model-index:
- name: tts-v0.3-finetuned
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.10.0`
```yaml
base_model: syvai/tts-v1-pretrained
# Automatically upload checkpoint and final model to HF
hub_model_id: syvai/tts-v0.3-finetuned

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

datasets:
  - path: syvai/zac-coral-tts
    type: 
  - path: syvai/zac-dk-voice-pro
    type:
  - path: syvai/zac-dk-voice-single-speaker
    type:
dataset_prepared_path: last_run_prepared
val_set_size: 0.01
eval_sample_packing: False
output_dir: ./outputs/finetuned

sequence_len: 8196
sample_packing: true
pad_to_sequence_len: true

wandb_project: orph
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 2e-5

bf16: auto
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_steps: 3
evals_per_epoch: 5
saves_per_epoch: 5
weight_decay: 0.05

special_tokens:
  pad_token: <custom_token_7>

```

</details><br>

# tts-v0.3-finetuned

This model is a fine-tuned version of [syvai/tts-v1-pretrained](https://huggingface.co/syvai/tts-v1-pretrained) on the syvai/zac-coral-tts, the syvai/zac-dk-voice-pro and the syvai/zac-dk-voice-single-speaker datasets.
It achieves the following results on the evaluation set:
- Loss: 4.3861

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 3
- training_steps: 159

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log        | 0      | 0    | 4.9462          |
| 4.6427        | 0.2042 | 11   | 4.6525          |
| 4.5404        | 0.4084 | 22   | 4.5458          |
| 4.4701        | 0.6125 | 33   | 4.4809          |
| 4.4139        | 0.8167 | 44   | 4.4405          |
| 4.4146        | 1.0186 | 55   | 4.4182          |
| 4.4021        | 1.2227 | 66   | 4.4045          |
| 4.3951        | 1.4269 | 77   | 4.3957          |
| 4.3845        | 1.6311 | 88   | 4.3906          |
| 4.3651        | 1.8353 | 99   | 4.3880          |
| 4.3924        | 2.0371 | 110  | 4.3867          |
| 4.3551        | 2.2413 | 121  | 4.3865          |
| 4.3478        | 2.4455 | 132  | 4.3861          |
| 4.3894        | 2.6497 | 143  | 4.3859          |
| 4.3801        | 2.8538 | 154  | 4.3861          |


### Framework versions

- Transformers 4.52.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1