---
language:
- sv
license: mit
tags:
- common_voice
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
model-index:
- name: SpeechT5 TTS Swedish
  results: []
pipeline_tag: text-to-speech
inference: false
---

<!-- 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. -->

# SpeechT5 TTS Swedish

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Common Voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4621

## Model description

Swedish SpeechT5 model trained on Swedish language in Common Voice. Example on how to implement the model below. Test the model yourself at [https://huggingface.co/spaces/GreenCounsel/SpeechT5-sv](https://huggingface.co/spaces/GreenCounsel/SpeechT5-sv) (not possible to run pipeline inference at Huggingface).

```
#pip install datasets soundfile 
#pip install transformers
#pip install sentencepiece

from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan, set_seed
import torch

processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
model = SpeechT5ForTextToSpeech.from_pretrained("GreenCounsel/speecht5_tts_common_voice_5_sv")
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")

repl = [
    ('Ä', 'ae'),
    ('Å', 'o'),
    ('Ö', 'oe'),
    ('ä', 'ae'),
    ('å', 'o'),
    ('ö', 'oe'),
    ('ô','oe'),
    ('-',''),
    ('‘',''),
    ('’',''),
    ('“',''),
    ('”',''),

]

from datasets import load_dataset
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")

speaker_embeddings = torch.tensor(embeddings_dataset[7000]["xvector"]).unsqueeze(0)
set_seed(555)

text="Förstår du vad han menar?"
for src, dst in repl:
       text = text.replace(src, dst)
inputs = processor(text=text, return_tensors="pt")

speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)

import soundfile as sf
sf.write("output.wav", speech.numpy(), samplerate=16000)

```

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5349        | 4.8   | 1000 | 0.4953          |
| 0.5053        | 9.59  | 2000 | 0.4714          |
| 0.5032        | 14.39 | 3000 | 0.4646          |
| 0.4958        | 19.18 | 4000 | 0.4621          |


### Framework versions

- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3