AI4Bharat / IndicConformerASRLinks
☆51Updated 7 months ago
Alternatives and similar repositories for IndicConformerASR
Users that are interested in IndicConformerASR are comparing it to the libraries listed below
Sorting:
- Indic TTS for Indian Languages: This is a project on developing text-to-speech (TTS) synthesis systems for Indian languages, improving qu…☆53Updated last week
- Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR☆73Updated 8 months ago
- Text-to-Speech for languages of India☆332Updated last year
- Finetune VITS and MMS using HuggingFace's tools☆191Updated last year
- Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.☆358Updated 2 years ago
- ☆82Updated 4 months ago
- Real-time Voice Activity Detection (VAD) with some example use case like simple voice bot and live transcription (realtime transcription)☆104Updated 5 months ago
- ☆193Updated last year
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆295Updated 8 months ago
- This is an on-CPU real-time conversational system for two-way speech communication with AI models, utilizing a continuous streaming archi…☆236Updated 2 months ago
- A Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS☆54Updated last year
- ☆323Updated last year
- A simple, consistent and extendable toolkit for IndicTrans2. (Pypi: https://pypi.org/project/indictranstoolkit)☆37Updated 6 months ago
- A python package for whisper normalizer☆75Updated 4 months ago
- ☆64Updated 7 months ago
- Joint speech-language model - respond directly to audio!☆372Updated last year
- Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2☆103Updated 5 months ago
- Bangla TTS Inference pipeline using Vit TTS☆13Updated last year
- Traditional ASR (Signal & Cepstral Analysis, DTW, HMM) & DNNs (Custom Models + DeepSpeech) on Indian Accent Speech☆92Updated 2 years ago
- Fine Tune the Style-TTS2 Voice Model☆266Updated 7 months ago
- ☆50Updated 3 years ago
- Vaksanca introduces free Sanskrit speech corpus with vowel segmentation.☆16Updated 4 years ago
- ☆45Updated 3 years ago
- Whisper finetuning☆15Updated 10 months ago
- ☆261Updated 8 months ago
- This project is about performing Speaker diarization for Hindi Language.☆59Updated 4 years ago
- VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency☆185Updated 3 months ago
- Swarah: Indian-English speech dataset collected across the country☆37Updated 7 months ago
- A streaming whisper server for on-prem transcription☆23Updated last year
- 🎙️ Arabic TTS models (Tacotron2, FastPitch)☆135Updated last month