T5 model optimized with FlexAttention
☆14Sep 30, 2024Updated 2 years ago
Alternatives and similar repositories for t5-flex-attention
Users that are interested in t5-flex-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Text-To-Speech for NotebookLM☆40Jul 20, 2025Updated last year
- Customized Seed-VC implementation☆14Updated this week
- This is the repository for the work "DegVoC: Rethinking Neural Vocoder from a Degradation Perspective", which is accepted at AAAI 2026.☆13Apr 29, 2026Updated 6 months ago
- pytorch model for contexless-phoneme prediction from speech audio☆32Oct 30, 2025Updated last year
- ☆19Mar 22, 2024Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Evaluation code for the Interspeech publication "Towards Frame-level Quality Predictions of Synthetic Speech". Evaluate frame-level repre…☆14Aug 15, 2025Updated last year
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆17May 20, 2025Updated last year
- Voxtral Codec : Combining Semantic VQ and Acoustic FSQ for Ultra-Low Bitrate Speech Generation (Voxtral TTS Backbone)☆18Updated this week
- ☆19Aug 13, 2026Updated 2 months ago
- PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors☆26Updated this week
- ☆23Oct 17, 2024Updated 2 years ago
- ☆14Dec 13, 2024Updated last year
- ☆35Sep 6, 2025Updated last year
- Forced alignment decoder for Whisper.☆16Mar 13, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆39Jun 9, 2025Updated last year
- PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind☆72Oct 24, 2026Updated 2 weeks ago
- Glow-TTS with Stochastic Duration Predictor and Stochastic Pitch Predictor☆20Jun 5, 2023Updated 3 years ago
- This is the repository for the work "BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective".☆67Nov 5, 2025Updated last year
- ☆27Jul 3, 2026Updated 4 months ago
- Train no-reference speech quality estimators with multiple datasets via learned, per-dataset alignments.☆20Aug 1, 2025Updated last year
- Speech Resynthesis and Language Modeling☆27Jun 11, 2025Updated last year
- Official implementation of Contextual Speech Extraction (ICASSP 2025)☆11Mar 17, 2025Updated last year
- Voice Agent implementations for the VAmoS Benchmark☆19Sep 4, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Inference for the STFT-VAE continuous audio codec (24kHz, 3.125Hz latent)☆48Jul 12, 2026Updated 3 months ago
- Simple tool for speech dataset augmentation for modeling various prosodies.☆14Jan 14, 2021Updated 5 years ago
- trying to reproduce suno v3☆37Jan 29, 2025Updated last year
- NVV-SuperBench: Beyond Words, Beyond Quality—Benchmarking Nonverbal Vocalizations in Speech Generation (Interspeech 2026 long paper)☆20Jun 21, 2026Updated 4 months ago
- A Neural Audio Codec (NAC) for Universal Audio☆48May 30, 2025Updated last year
- A lightweight library for normalizing speech transcripts before computing WER☆29Oct 29, 2026Updated last week
- Phoneme alignment based on a variational autoencoder (VAE) and self-supervised learning (SSL) acoustic features.☆42Aug 24, 2026Updated 2 months ago
- FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis (Accepted by ISCSLP'2024)☆26Feb 22, 2024Updated 2 years ago
- Open, reproducible TTS/STT evaluation toolkit: WER/CER via Whisper ASR, NISQAv2, audio health, and prosody metrics with offline black-and…☆42Sep 9, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆28Nov 15, 2023Updated 2 years ago
- [ACL 2026 Findings] Affectron: Emotional Speech Synthesis with Affective and Contextually Aligned Nonverbal Vocalizations☆21Jul 16, 2026Updated 3 months ago
- Implementation of the paper "BERTphone: Phonetically-aware Encoder Representations for Utterance-level Speaker and Language Recognition"☆17Dec 10, 2020Updated 5 years ago
- ☆29Jun 22, 2026Updated 4 months ago
- 60k hours of phoneme-aligned audio from audio books☆19Jul 27, 2024Updated 2 years ago
- Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"☆11Apr 10, 2025Updated last year
- Wenet speech to text for react native☆10Nov 1, 2022Updated 4 years ago