Parler-TTS Mini v1.1

Parler-TTS Mini v1.1 is a lightweight text-to-speech (TTS) model, trained on 45K hours of audio data, that can generate high-quality, natural sounding speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).

🚨 Parler-TTS Mini v1.1 is the exact same model than Mini v1. It was trained on the same datasets and with the same training configuration. The only change is the use of a better prompt tokenizer. This tokenizer has a larger vocabulary and handles byte fallback, which simplifies multilingual training. It's based on unsloth/llama-2-7b tokenizer. Thanks to the AI4Bharat team who provided advice and assistance in improving tokenization. 🚨

📖 Quick Index

• 👨‍💻 Installation
• 🎲 Using a random voice
• 🎯 Using a specific speaker
• Motivation
• Optimizing inference

🛠️ Usage

🚨Unlike previous versions of Parler-TTS, here we use two tokenizers - one for the prompt and one for the description.🚨

👨‍💻 Installation

Using Parler-TTS is as simple as "bonjour". Simply install the library once:

pip install git+https://github.com/huggingface/parler-tts.git

🎲 Random voice

Parler-TTS has been trained to generate speech with features that can be controlled with a simple text prompt, for example:

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-v1.1").to(device)
tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-mini-v1.1")
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)

🎯 Using a specific speaker

To ensure speaker consistency across generations, this checkpoint was also trained on 34 speakers, characterized by name (e.g. Jon, Lea, Gary, Jenna, Mike, Laura).

To take advantage of this, simply adapt your text description to specify which speaker to use: Jon's voice is monotone yet slightly fast in delivery, with a very close recording that almost has no background noise.

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-v1.1").to(device)
tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-mini-v1.1")
description_tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder._name_or_path)

prompt = "Hey, how are you doing today?"
description = "Jon's voice is monotone yet slightly fast in delivery, with a very close recording that almost has no background noise."

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 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 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 - you can train and fine-tuned your own version of the model.
• The Data-Speech repository - a suite of utility scripts designed to annotate speech datasets.
• The Parler-TTS organization - 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.