freds0

This model is a fine-tuned version of distil-whisper-large-v3 for automatic speech recognition (ASR) in Brazilian Portuguese. It was trained using the Common Voice 16 dataset in conjunction with a private dataset transcribed using Whisper Large v3. The model aims to perform automatic speech transcription in Brazilian Portuguese with high accuracy. By combining data from Common Voice 16 with an automatically transcribed private dataset, the model achieved a Word Error Rate (WER) of 8.221% on the validation set of Common Voice 16. - Model type: Speech recognition model based on distil-whisper-large-v3 - Language(s) (NLP): Brazilian Portuguese (pt-BR) - License: MIT - Finetuned from model [optional]: distil-whisper/distil-large-v3 You can use the model with the Transformers library: from transformers import WhisperForConditionalGeneration, WhisperProcessor

Parler-TTS Mini Multilingual v1 is a multilingual extension of Parler-TTS Mini. It is a fine-tuned version, trained on BRSpeech-TTS-Dataset. In all, this represents some 200 hours of portuguese data. Parler-TTS Mini Portuguese can speak in Brazilian Portuguese 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. 🚨 This work is the result of a collaboration between the HuggingFace audio team and the Quantum Squadra team. The AI4Bharat team also provided advice and assistance in improving tokenization. 🚨 📖 Quick Index 👨‍💻 Installation 🎯 Inference Motivation Optimizing inference 🚨Unlike previous versions of Parler-TTS, here we use two tokenizers - one for the prompt and one for the description.🚨 Using Parler-TTS is as simple as "bonjour". Simply install the library once: Parler-TTS has been trained to generate speech with features that can be controlled with a simple text prompt, for example: 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 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. If you found this repository useful, please consider citing this work and also the original Stability AI paper: This model is permissively licensed under the Apache 2.0 license.