daanzu / speech-training-recorder
Simple GUI application to help record audio dictated from given text prompts, for use with training speech recognition or speech synthesis.
☆39Updated 3 years ago
Related projects: ⓘ
- Stable timestamps and confidence score for words of OpenAI's Whisper outputs down to word-level.☆25Updated last year
- Docker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-gramma…☆20Updated 2 years ago
- Zero-shot multimodal punctuation insertion and truecasing using Whisper☆95Updated last year
- automatically align transcribed audio and generate a wav2letter training corpus☆34Updated last year
- 🌼 Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition☆14Updated 6 months ago
- Create an LJSpeech structured voice dataset on wave input☆16Updated 2 months ago
- Google's SoundStorm: Efficient Parallel Audio Generation☆115Updated last year
- A high-quality, varied ~30hr voice dataset suitable for training a TTS model☆55Updated last year
- Go from raw audio files to a text-audio dataset automatically with OpenAI's Whisper.☆132Updated last year
- On-device speaker diarization powered by deep learning☆22Updated 3 weeks ago
- An unofficial PyTorch implementation of the StreamVC(Real-Time Low-Latency Voice Conversion)☆104Updated last month
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆74Updated 2 months ago
- On-device voice activity detection (VAD) powered by deep learning☆165Updated 2 weeks ago
- Simplified diarization pipeline using some pretrained models - audio file to diarized segments in a few lines of code☆132Updated 4 months ago
- NPTEL2020: Speech2Text dataset for Indian-English Accent☆69Updated 2 years ago
- Experiments to test different speech recognition systems for SEPIA Framework☆57Updated last year
- ☆30Updated 7 months ago
- Tools to create your own voice dataset for TTS training☆58Updated 3 years ago
- PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supp…☆45Updated last year
- Reproducible experimental protocols for multimedia (audio, video, text) database☆79Updated 5 months ago
- The human speaks a language with an accent. A particular accent necessarily reflects a person's linguistic background. The model defines …☆54Updated 2 years ago
- 🐸TTS recipes for different datasets☆84Updated 2 years ago
- Speaker diarization model☆18Updated last year
- On-device noise suppression powered by deep learning☆59Updated 2 weeks ago
- STT Service based on Kaldi ASR☆15Updated 6 years ago
- ☆75Updated 3 months ago
- A speaker embedding network in Pytorch that is very quick to set up and use for whatever purposes.☆82Updated last year
- 🐍 Coqui's machine learning job scheduler☆31Updated 3 years ago
- Speaker change detection using SincNet and an LSTM/Transformer☆39Updated 2 months ago
- VALL-E 2 reproduction☆72Updated 2 months ago