Skip to content

indri-voice/indri

Repository files navigation

Live Demo Twitter Hugging Face Collection Hugging Face Spaces Release Blog

Indri

Indri is a series of multilingual audio models that can do TTS, ASR, and audio continuation. It currently supports these languages:

  1. English
  2. Hindi

This repo hosts the inference code for inference of Indri models.

Samples

Text Sample
मित्रों, हम आज एक नया छोटा और शक्तिशाली मॉडल रिलीज कर रहे हैं। Sample
भाइयों और बहनों, ये हमारा सौभाग्य है कि हम सब मिलकर इस महान देश को नई ऊंचाइयों पर ले जाने का सपना देख रहे हैं। Sample
Hello दोस्तों, future of speech technology mein अपका स्वागत है Sample
In this model zoo, a new model called Indri has appeared. Sample

Key features

  1. Extremely small, based on GPT-2 small architecture. The methodology can be extended to any autoregressive transformer-based architecture.
  2. Ultra-fast. Using our self hosted service option, on RTX6000Ada NVIDIA GPU the model can achieve speeds up to 400 toks/s (4s of audio generation per s) and under 20ms time to first token for the 124m model.
  3. On RTX6000Ada, it can support a batch size of ~1000 sequences with full context length of 1024 tokens
  4. Supports voice cloning with small prompts (<5s).
  5. Code mixing text input in 2 languages - English and Hindi.

Details

  1. Model Type: GPT-2 based language model
  2. Size: 124M parameters
  3. Language Support: English, Hindi
  4. License: This model is not for commercial usage. This is only a research showcase.

Here's a brief of how the model works:

  1. Converts input text into tokens
  2. Runs autoregressive decoding on GPT-2 based transformer model and generates audio tokens
  3. Decodes audio tokens (using Kyutai/mimi) to audio

Please read our blog here for more technical details on how it was built.

How to Get Started with the Model

🤗 pipelines

Use the code below to get started with the model. Pipelines are the best way to get started with the model.

import torch
import torchaudio
from transformers import pipeline

model_id = '11mlabs/indri-0.1-124m-tts'
task = 'indri-tts'

pipe = pipeline(
    task,
    model=model_id,
    device=torch.device('cuda:0'), # Update this based on your hardware,
    trust_remote_code=True
)

output = pipe(['Hi, my name is Indri and I like to talk.'], speaker = '[spkr_63]')

torchaudio.save('output.wav', output[0]['audio'][0], sample_rate=24000)

Available speakers

Speaker ID Speaker name
[spkr_63] 🇬🇧 👨 book reader
[spkr_67] 🇺🇸 👨 influencer
[spkr_68] 🇮🇳 👨 book reader
[spkr_69] 🇮🇳 👨 book reader
[spkr_70] 🇮🇳 👨 motivational speaker
[spkr_62] 🇮🇳 👨 book reader heavy
[spkr_53] 🇮🇳 👩 recipe reciter
[spkr_60] 🇮🇳 👩 book reader
[spkr_74] 🇺🇸 👨 book reader
[spkr_75] 🇮🇳 👨 entrepreneur
[spkr_76] 🇬🇧 👨 nature lover
[spkr_77] 🇮🇳 👨 influencer
[spkr_66] 🇮🇳 👨 politician

Self hosted service

git clone https://github.com/cmeraki/indri.git
cd indri
pip install -r requirements.txt

# Install ffmpeg (for Mac/Windows, refer here: https://www.ffmpeg.org/download.html)
sudo apt update -y
sudo apt upgrade -y
sudo apt install ffmpeg -y

python -m server --model_path 11mlabs/indri-0.1-124m-tts --device cuda:0 --port 8000

Defaults:

  • device: cuda:0
  • port: 8000

Choices:

Redirect to http://localhost:8000/docs to see the API documentation and test the service.

To run the GGUF quantized models, follow the instructions here.

Citation

If you use this model in your research, please cite:

@misc{indri-multimodal-alm,
  author       = {11mlabs},
  title        = {Indri: Multimodal audio language model},
  year         = {2024},
  publisher    = {GitHub},
  journal      = {GitHub Repository},
  howpublished = {\url{https://github.com/indri-voice/indri}},
  email        = {apurvagup@gmail.com, romit.73@gmail.com}
}

BibTex

  1. nanoGPT

  2. Kyutai/mimi

@techreport{kyutai2024moshi,
      title={Moshi: a speech-text foundation model for real-time dialogue},
      author={Alexandre D\'efossez and Laurent Mazar\'e and Manu Orsini and
      Am\'elie Royer and Patrick P\'erez and Herv\'e J\'egou and Edouard Grave and Neil Zeghidour},
      year={2024},
      eprint={2410.00037},
      archivePrefix={arXiv},
      primaryClass={eess.AS},
      url={https://arxiv.org/abs/2410.00037},
}
  1. Whisper
@misc{radford2022whisper,
  doi = {10.48550/ARXIV.2212.04356},
  url = {https://arxiv.org/abs/2212.04356},
  author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}
  1. silero-vad
@misc{Silero VAD,
  author = {Silero Team},
  title = {Silero VAD: pre-trained enterprise-grade Voice Activity Detector (VAD), Number Detector and Language Classifier},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/snakers4/silero-vad}},
  commit = {insert_some_commit_here},
  email = {hello@silero.ai}
}

About

omnimodal models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •