smtiitm / Fastspeech2_HSLinks
Indic TTS for Indian Languages: This is a project on developing text-to-speech (TTS) synthesis systems for Indian languages, improving quality of synthesis, as well as small foot print TTS integrated with disability aids and various other applications.
☆42Updated this week
Alternatives and similar repositories for Fastspeech2_HS
Users that are interested in Fastspeech2_HS are comparing it to the libraries listed below
Sorting:
- Text-to-Speech for languages of India☆275Updated 10 months ago
- ☆43Updated 3 months ago
- Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR☆62Updated 3 months ago
- Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.☆338Updated 2 years ago
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆279Updated 4 months ago
- Finetune VITS and MMS using HuggingFace's tools☆164Updated last year
- ☆169Updated 9 months ago
- ☆58Updated this week
- Indic TTS for Indian Languages: This is a project on developing text-to-speech (TTS) synthesis systems for Indian languages, improving qu…☆14Updated last year
- 🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.☆252Updated last year
- ☆377Updated last year
- Fine Tune the Style-TTS2 Voice Model☆252Updated 3 months ago
- ☆26Updated 7 months ago
- This is an on-CPU real-time conversational system for two-way speech communication with AI models, utilizing a continuous streaming archi…☆191Updated 5 months ago
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆208Updated 5 months ago
- ☆281Updated 2 months ago
- StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion☆185Updated last year
- VoiceBench: Benchmarking LLM-Based Voice Assistants☆286Updated last month
- finetune llm part for spark-tts model☆109Updated 6 months ago
- Real-time Voice Activity Detection (VAD) with some example use case like simple voice bot and live transcription (realtime transcription)☆98Updated last month
- VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency☆59Updated this week
- Real-time Speech-Text Foundation Model Toolkit (wip)☆246Updated 6 months ago
- Update ASR paper everyday☆329Updated last week
- Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2☆90Updated 3 weeks ago
- ☆274Updated last year
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆123Updated 2 months ago
- PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models☆741Updated last week
- [INTERSPEECH 2024] EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark☆278Updated 5 months ago
- This project is about performing Speaker diarization for Hindi Language.☆49Updated 4 years ago
- ☆232Updated 4 months ago