🚀 SpeechT5 TTS Swedish
This model is a fine - tuned version of microsoft/speecht5_tts on the Common Voice dataset, used for Swedish text - to - speech conversion.
🚀 Quick Start
This Swedish SpeechT5 model is trained on the Swedish language in the Common Voice dataset. You can test the model yourself at https://huggingface.co/spaces/GreenCounsel/SpeechT5-sv (it's not possible to run pipeline inference at Huggingface).
💻 Usage Examples
Basic Usage
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)
📚 Documentation
This model achieves the following results on the evaluation set:
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
📄 License
This project is under the MIT license.
📦 Information
Property |
Details |
Model Type |
Fine - tuned SpeechT5 model for Swedish text - to - speech |
Training Data |
mozilla - foundation/common_voice_13_0 |
Pipeline Tag |
text - to - speech |
Inference |
false |
Tags |
common_voice, generated_from_trainer |
Language |
sv |