---
library_name: transformers
tags:
- text-to-speech
- annotation
license: apache-2.0
language:
- en
- fr
- es
- pt
- pl
- de
- nl
- it
pipeline_tag: text-to-speech
inference: false
datasets:
- facebook/multilingual_librispeech
- PHBJT/cml-tts-cleaned-levenshtein
- PHBJT/multilingual_librispeech_text_description_capitalized
- PPHBJT/cml-tts-description-punctuation-and-casing-restored
- parler-tts/libritts_r_filtered
- parler-tts/libritts-r-filtered-speaker-descriptions
- parler-tts/mls_eng
- parler-tts/mls-eng-speaker-descriptions
---
# Parler-TTS Mini Multilingual
**Parler-TTS Mini Multilingual v1.1** is a multilingual extension of [Parler-TTS Mini](https://huggingface.co/parler-tts/parler-tts-mini-v1.1).
It is a fine-tuned version, trained on a [cleaned version](https://huggingface.co/datasets/PHBJT/cml-tts-cleaned-levenshtein) of [CML-TTS](https://huggingface.co/datasets/ylacombe/cml-tts) and on the non-English version of [Multilingual LibriSpeech](https://huggingface.co/datasets/facebook/multilingual_librispeech).
In all, this represents some 9,200 hours of non-English data. To retain English capabilities, we also added back the [LibriTTS-R English dataset](https://huggingface.co/datasets/parler-tts/libritts_r_filtered), some 580h of high-quality English data.
**Parler-TTS Mini Multilingual** can speak in 7 European languages: English, French, Spanish, Portuguese, Polish, German, Italian and Dutch.
Thanks to its **better prompt tokenizer**, it can easily be extended to other languages. This tokenizer has a larger vocabulary and handles byte fallback, which simplifies multilingual training.
π¨ This work is the result of a collaboration between the **HuggingFace audio team** and the **[Quantum Squadra](https://quantumsquadra.com/) team**. The **[AI4Bharat](https://ai4bharat.iitm.ac.in/) team** also provided advice and assistance in improving tokenization. π¨
## π Quick Index
* [π¨βπ» Installation](#π¨βπ»-installation)
* [π² Using a random voice](#π²-random-voice)
* [π― Using a specific speaker](#π―-using-a-specific-speaker)
* [Motivation](#motivation)
* [Optimizing inference](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md)
## π οΈ Usage
π¨Unlike previous versions of Parler-TTS, here we use two tokenizers - one for the prompt and one for the description.π¨
### π¨βπ» Installation
Using Parler-TTS is as simple as "bonjour". Simply install the library once:
```sh
pip install git+https://github.com/huggingface/parler-tts.git
```
### Inference
**Parler-TTS** has been trained to generate speech with features that can be controlled with a simple text prompt, for example:
```py
import torch
from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer
import soundfile as sf
device = "cuda:0" if torch.cuda.is_available() else "cpu"
model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-mini-multilingual").to(device)
tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-mini-multilingual")
description_tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder._name_or_path)
prompt = "Hey, how are you doing today?"
description = "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."
input_ids = description_tokenizer(description, return_tensors="pt").input_ids.to(device)
prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
audio_arr = generation.cpu().numpy().squeeze()
sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)
```
**Tips**:
* We've set up an [inference guide](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md) to make generation faster. Think SDPA, torch.compile, batching and streaming!
* Include the term "very clear audio" to generate the highest quality audio, and "very noisy audio" for high levels of background noise
* Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech
* The remaining speech features (gender, speaking rate, pitch and reverberation) can be controlled directly through the prompt
## Motivation
Parler-TTS is a reproduction of work from the paper [Natural language guidance of high-fidelity text-to-speech with synthetic annotations](https://www.text-description-to-speech.com) by Dan Lyth and Simon King, from Stability AI and Edinburgh University respectively.
Contrarily to other TTS models, Parler-TTS is a **fully open-source** release. All of the datasets, pre-processing, training code and weights are released publicly under permissive license, enabling the community to build on our work and develop their own powerful TTS models.
Parler-TTS was released alongside:
* [The Parler-TTS repository](https://github.com/huggingface/parler-tts) - you can train and fine-tuned your own version of the model.
* [The Data-Speech repository](https://github.com/huggingface/dataspeech) - a suite of utility scripts designed to annotate speech datasets.
* [The Parler-TTS organization](https://huggingface.co/parler-tts) - where you can find the annotated datasets as well as the future checkpoints.
## Citation
If you found this repository useful, please consider citing this work and also the original Stability AI paper:
```
@misc{lacombe-etal-2024-parler-tts,
author = {Yoach Lacombe and Vaibhav Srivastav and Sanchit Gandhi},
title = {Parler-TTS},
year = {2024},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/huggingface/parler-tts}}
}
```
```
@misc{lyth2024natural,
title={Natural language guidance of high-fidelity text-to-speech with synthetic annotations},
author={Dan Lyth and Simon King},
year={2024},
eprint={2402.01912},
archivePrefix={arXiv},
primaryClass={cs.SD}
}
```
## License
This model is permissively licensed under the Apache 2.0 license.