text-to-text-transfer-transformer
tortoise-tts
text-to-text-transfer-transformer | tortoise-tts | |
---|---|---|
29 | 144 | |
5,909 | 11,819 | |
1.1% | - | |
5.0 | 8.0 | |
3 months ago | about 9 hours ago | |
Python | Jupyter Notebook | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
text-to-text-transfer-transformer
- T5: Text-to-Text-Transfer-Transformer
-
Gemma: New Open Models
Google released the T5 paper about 5 years ago:
https://arxiv.org/abs/1910.10683
This included full model weights along with a detailed description of the dataset, training process, and ablations that led them to that architecture. T5 was state-of-the-art on many benchmarks when it was released, but it was of course quickly eclipsed by GPT-3.
Following GPT-3, it became much more common for labs to not release full details or model weights. Prior to that, it was common practice from Google (BERT, T5), Meta (BART), OpenAI (GPT1, GPT2) and others to release full training details and model weights.
-
[P] Free and Fast LLM Finetuning
[2] - https://arxiv.org/abs/1910.10683
- Free and Fast LLM Finetuning
-
[Discussion] Is there a better way than positional encodings in self attention?
T5-style relative encodings https://arxiv.org/abs/1910.10683
-
What were the 40 research papers on the list Ilya Sutskever gave John Carmack?
11. T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer" (2020) - https://arxiv.org/abs/1910.10683 (Google Research)
-
[P] T5 Implementation in PyTorch
You can find a link to the paper here: https://arxiv.org/abs/1910.10683
-
Text-to-Text Transformer (T5-Base Model) Testing For Summarization, Sentiment Classification, and Translation Using Pytorch and Torchtext
The Text-to-Text Transformer is a type of neural network architecture that is particularly well-suited for natural language processing tasks involving the generation of text. It was introduced in the paper "Attention is All You Need" by Vaswani et al. and has since become a popular choice for many NLP tasks, including language translation, summarization, and text generation
- AlphaCode by DeepMind
-
[R] LiBai: a large-scale open-source model training toolbox
Found relevant code at https://github.com/google-research/text-to-text-transfer-transformer + all code implementations here
tortoise-tts
- FLaNK Stack Weekly 12 February 2024
-
OpenVoice: Versatile Instant Voice Cloning
I use Tortoise TTS. It's slow, a little clunky, and sometimes the output gets downright weird. But it's the best quality-oriented TTS I've found that I can run locally.
https://github.com/neonbjb/tortoise-tts
- [discussion] text to voice generation for textbooks
- DALL-E 3: Improving image generation with better captions [pdf]
-
Open Source Libraries
neonbjb/tortoise-tts
-
Running Tortoise-TTS - IndexError: List out of range
EDIT: It appears to be the exact same issue as this
-
My Deep Learning Rig
It was primarily being used to train TTS models (see https://github.com/neonbjb/tortoise-tts), which largely fit into a single GPUs memory. So, for data parallelism, x8 PCIe isn't that much of a concern.
-
PlayHT2.0: State-of-the-Art Generative Voice AI Model for Conversational Speech
Previously TortoiseTTS was associated with PlayHT in some way, although the exact connection is a bit vague [0].
From the descriptions here it sounds a lot like AudioLM / SPEAR TTS / some of Meta's recent multilingual TTS approaches, although those models are not open source, sounds like PlayHT's approach is in a similar spirit. The discussion of "mel tokens" is closer to what I would call the classic TTS pipeline in many ways... PlayHT has generally been kind of closed about what they used, would be interesting to know more.
I assume the key factor here is high quality, emotive audio with good data cleaning processes. Probably not even a lot of data, at least in the scale of "a lot" in speech, e.g. ASR (millions of hours) or TTS (hundreds to thousands). As opposed to some radically new architectural piece never before seen in the literature, there are lots of really nice tools for emotive and expressive TTS buried in recent years of publications.
Tacotron 2 is perfectly capable of this type of stuff as well, as shown by Dessa [1] a few years ago (this writeup is a nice intro to TTS concepts). With the limit largely being, at some point you haven't heard certain phonetic sounds before in a voice, and need to do something to get plausible outcomes for new voices.
[0] Discussion here https://github.com/neonbjb/tortoise-tts/issues/182#issuecomm...
[1] https://medium.com/dessa-news/realtalk-how-it-works-94c1afda...
-
Comparing Tortoise and Bark for Voice Synthesis
Tortoise GitHub repo - Source code, documentation, and usage guide
-
Show HN: Gdańsk AI – full stack AI voice chatbot (STT, LLM, TTS, auth, payments)
TorToiSe (https://github.com/neonbjb/tortoise-tts) produces the best quality speech of any freely available model. However, its long inference times makes it impractical for voice chatbots like Gdansk.
What are some alternatives?
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DeepCreamPy - Decensoring Hentai with Deep Neural Networks
bark - 🔊 Text-Prompted Generative Audio Model
dalle-mini - DALL·E Mini - Generate images from a text prompt
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
piper - A fast, local neural text to speech system
majesty-diffusion - Majesty Diffusion by @Dango233(@Dango233max) and @apolinario (@multimodalart)
tacotron2 - Tacotron 2 - PyTorch implementation with faster-than-realtime inference
nlu - 1 line for thousands of State of The Art NLP models in hundreds of languages The fastest and most accurate way to solve text problems.
larynx - End to end text to speech system using gruut and onnx