Speecht5 Tts

🚀 SpeechT5 (TTS task)

The SpeechT5 model fine-tuned for speech synthesis (text-to-speech) on LibriTTS, offering high - quality text - to - speech conversion.

🚀 Quick Start

The SpeechT5 model is a powerful tool for speech synthesis. You can quickly get started with it using the following steps.

🤗 Transformers Usage

You can run SpeechT5 TTS locally with the 🤗 Transformers library.

1. First install the 🤗 Transformers library, sentencepiece, soundfile and datasets(optional):

pip install --upgrade pip
pip install --upgrade transformers sentencepiece datasets[audio]

2. Run inference via the Text - to - Speech (TTS) pipeline. You can access the SpeechT5 model via the TTS pipeline in just a few lines of code!

from transformers import pipeline
from datasets import load_dataset
import soundfile as sf

synthesiser = pipeline("text-to-speech", "microsoft/speecht5_tts")

embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.

speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})

sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])

3. Run inference via the Transformers modelling code - You can use the processor + generate code to convert text into a mono 16 kHz speech waveform for more fine - grained control.

from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
from datasets import load_dataset
import torch
import soundfile as sf
from datasets import load_dataset

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

inputs = processor(text="Hello, my dog is cute.", return_tensors="pt")

# load xvector containing speaker's voice characteristics from a dataset
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)

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

sf.write("speech.wav", speech.numpy(), samplerate=16000)

Fine - tuning the Model

Refer to [this Colab notebook](https://colab.research.google.com/drive/1i7I5pzBcU3WDFarDnzweIj4 - sVVoIUFJ) for an example of how to fine - tune SpeechT5 for TTS on a different dataset or a new language.

✨ Features

• Unified - Modal Framework: Motivated by the success of T5 in pre - trained natural language processing models, SpeechT5 proposes a unified - modal framework that explores encoder - decoder pre - training for self - supervised speech/text representation learning.
• Cross - Modal Vector Quantization: To align textual and speech information into a unified semantic space, a cross - modal vector quantization approach is proposed, which randomly mixes up speech/text states with latent units as the interface between encoder and decoder.
• Wide Application Range: Extensive evaluations show its superiority on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification.

📦 Installation

First, you need to install the necessary libraries:

pip install --upgrade pip
pip install --upgrade transformers sentencepiece datasets[audio]

💻 Usage Examples

Basic Usage

from transformers import pipeline
from datasets import load_dataset
import soundfile as sf

synthesiser = pipeline("text-to-speech", "microsoft/speecht5_tts")

embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.

speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})

sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])

Advanced Usage

from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
from datasets import load_dataset
import torch
import soundfile as sf
from datasets import load_dataset

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

inputs = processor(text="Hello, my dog is cute.", return_tensors="pt")

# load xvector containing speaker's voice characteristics from a dataset
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)

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

sf.write("speech.wav", speech.numpy(), samplerate=16000)

📚 Documentation

Model Description

Motivated by the success of T5 (Text - To - Text Transfer Transformer) in pre - trained natural language processing models, we propose a unified - modal SpeechT5 framework that explores the encoder - decoder pre - training for self - supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder - decoder network and six modal - specific (speech/text) pre/post - nets. After preprocessing the input speech/text through the pre - nets, the shared encoder - decoder network models the sequence - to - sequence transformation, and then the post - nets generate the output in the speech/text modality based on the output of the decoder.

Leveraging large - scale unlabeled speech and text data, we pre - train SpeechT5 to learn a unified - modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross - modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder.

Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification.

Model Sources

• Repository: [https://github.com/microsoft/SpeechT5/]
• Paper: [https://arxiv.org/pdf/2110.07205.pdf]
• Blog Post: [https://huggingface.co/blog/speecht5]
• Demo: [https://huggingface.co/spaces/Matthijs/speecht5 - tts - demo]

Direct Use

You can use this model for speech synthesis. See the model hub to look for fine - tuned versions on a task that interests you.

Training Details

Training Data

LibriTTS

Training Procedure

Preprocessing

Leveraging large - scale unlabeled speech and text data, we pre - train SpeechT5 to learn a unified - modal representation, hoping to improve the modeling capability for both speech and text.

Training hyperparameters

• Precision: [More Information Needed]
• Regime: [More Information Needed]

🔧 Technical Details

Model Architecture and Objective

The SpeechT5 framework consists of a shared encoder - decoder network and six modal - specific (speech/text) pre/post - nets. After preprocessing the input speech/text through the pre - nets, the shared encoder - decoder network models the sequence - to - sequence transformation, and then the post - nets generate the output in the speech/text modality based on the output of the decoder.

📄 License

The license used is MIT.

Citation

BibTeX:

@inproceedings{ao-etal-2022-speecht5,
    title = {{S}peech{T}5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing},
    author = {Ao, Junyi and Wang, Rui and Zhou, Long and Wang, Chengyi and Ren, Shuo and Wu, Yu and Liu, Shujie and Ko, Tom and Li, Qing and Zhang, Yu and Wei, Zhihua and Qian, Yao and Li, Jinyu and Wei, Furu},
    booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
    month = {May},
    year = {2022},
    pages={5723--5738},
}

Glossary

• text - to - speech: to synthesize audio