language:
- da
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- alexandrainst/nst-da
model-index:
- name: speecht5_tts-finetuned-nst-da
results: []
metrics:
- mse
pipeline_tag: text-to-speech
speecht5_tts-finetuned-nst-da
This model is a fine-tuned version of microsoft/speecht5_tts on the NST Danish ASR Database dataset. It achieves the following results on the evaluation set:
- Loss: 0.3738
Model description
Given that danish is a low-resource language, not many open-source implementations of a danish text-to-speech synthesizer are available online. As of writing, the only other existing implementations available on 🤗 are facebook/seamless-streaming and audo/seamless-m4t-v2-large. This model has been developed to provide a simpler alternative that still performs reasonable well, both in terms of output quality and inference time. Additionally, contrary to the aforementioned models, this model also has an associated Space on 🤗 at JackismyShephard/danish-speech-synthesis which provides an easy interface for danish text-to-speech synthesis, as well as optional speech enhancement.
Intended uses & limitations
The model is intended for danish text-to-speech synthesis.
The model does not recognize special symbols such as "æ", "ø" and "å", as it uses the default tokenizer of microsoft/speecht5_tts. The model performs best for short to medium length input text and expects input text to contain no more than 600 vocabulary tokens. Additionally, for best performance the model should be given a danish speaker embedding, ideally generated from an audio clip from the training split of alexandrainst/nst-da using speechbrain/spkrec-xvect-voxceleb.
The output of the model is a log-mel spectogram, which should be converted to a waveform using microsoft/speecht5_hifigan. For better quality output the resulting waveform can be enhanced using ResembleAI/resemble-enhance.
An example script showing how to use the model for inference can be found here.
Training and evaluation data
The model was trained and evaluated on alexandrainst/nst-da using MSE as both loss and metric.
Training procedure
The script used for training the model can be found here
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.463 | 1.0 | 4715 | 0.4169 |
| 0.4302 | 2.0 | 9430 | 0.3963 |
| 0.447 | 3.0 | 14145 | 0.3883 |
| 0.4283 | 4.0 | 18860 | 0.3847 |
| 0.394 | 5.0 | 23575 | 0.3830 |
| 0.3934 | 6.0 | 28290 | 0.3812 |
| 0.3928 | 7.0 | 33005 | 0.3795 |
| 0.4123 | 8.0 | 37720 | 0.3781 |
| 0.3851 | 9.0 | 42435 | 0.3785 |
| 0.4234 | 10.0 | 47150 | 0.3783 |
| 0.3781 | 11.0 | 51865 | 0.3759 |
| 0.3951 | 12.0 | 56580 | 0.3782 |
| 0.4073 | 13.0 | 61295 | 0.3757 |
| 0.4278 | 14.0 | 66010 | 0.3768 |
| 0.4172 | 15.0 | 70725 | 0.3747 |
| 0.3854 | 16.0 | 75440 | 0.3753 |
| 0.4876 | 17.0 | 80155 | 0.3741 |
| 0.432 | 18.0 | 84870 | 0.3738 |
| 0.4435 | 19.0 | 89585 | 0.3745 |
| 0.4255 | 20.0 | 94300 | 0.3739 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0