Fine tuned facebook/Wav2Vec2-960h-base for the purpose of speech based task detection relevant to banking and finances, of an individual.
Hindi Speech Dataset
A stripped down version of whisper.cpp - just the encoder
Пример использования распознавания речи SpeechKit на Java.
Omnilingual real-time Voice AI system using Meta’s OmniASR (omnilingual_1b) integrated with Sherpa-ONNX for offline transcription, enabling seamless speech-in / speech-out conversations across 1600+ languages
LISA: real-time speech-to-speech translation pipeline. faster-Whisper ASR → OPUS-MT neural translation (wait-k incremental algorithm) → Piper TTS. Supports 6 language pairs (EN↔DE/ES/FR). Docker Compose microservices. Targets p95 end-to-end latency <30s
Uzbek speech-to-text fine-tuning with Whisper-small for accurate, naturally formatted transcriptions.
Indian English Speech Dataset
British English Speech Dataset
Real-time speech-to-text app using Wav2Vec2 and Streamlit. Record from your browser and transcribe instantly.
ASR for end2end training by pytorch
A collection of Python scripts demonstrating how to run various AI tasks locally using models from the Hugging Face Hub and the transformers library (along with related libraries like datasets, sentence-transformers, etc.). These examples cover a range of modalities including text, vision, and audio, showcasing different models and pipelines.
American English Conversational Speech Dataset
Japanese Speech Dataset
A simple CRDNN based ASR model for my own understanding of how ASR works and are trained. (Work in progress) If anyone finds any error or have any suggestion please do let me know.
FastAPI-based Hindi ASR app using NVIDIA NeMo + ONNX, with Docker support for easy deployment.
Add a description, image, and links to the asr-model topic page so that developers can more easily learn about it.
To associate your repository with the asr-model topic, visit your repo's landing page and select "manage topics."