Pinned Repositories
android-vad
This VAD library can process audio in real-time utilizing GMM which helps identify presence of human speech in an audio sample that contains a mixture of speech and noise.
Ayase
🥥 Control everything by keyboard. Built for hackers and the blind.
CLIPfa
CLIPfa: Connecting Farsi Text and Images
ctcdecode-csharp
C# CTC Decoder bindings
dkakaie
Whatever
encodec.cpp
Port of Meta's Encodec in C/C++
fast-whisper-finetuning
fastconformer-ctc-telugu
NVIDIA NeMo's stt_en_fastconformer_ctc_large finetuned on open-source telugu data for Automatic Speech Recognition
shano-asosoft-results
WER/CER results for Asosoft speech corpus test set
train-whisper
Training script for Whisper ASR model
dkakaie's Repositories
dkakaie/train-whisper
Training script for Whisper ASR model
dkakaie/shano-asosoft-results
WER/CER results for Asosoft speech corpus test set
dkakaie/fast-whisper-finetuning
dkakaie/android-vad
This VAD library can process audio in real-time utilizing GMM which helps identify presence of human speech in an audio sample that contains a mixture of speech and noise.
dkakaie/Ayase
🥥 Control everything by keyboard. Built for hackers and the blind.
dkakaie/CLIPfa
CLIPfa: Connecting Farsi Text and Images
dkakaie/ctcdecode-csharp
C# CTC Decoder bindings
dkakaie/dkakaie
Whatever
dkakaie/encodec.cpp
Port of Meta's Encodec in C/C++
dkakaie/fastconformer-ctc-telugu
NVIDIA NeMo's stt_en_fastconformer_ctc_large finetuned on open-source telugu data for Automatic Speech Recognition
dkakaie/GrpcAudioStreaming
A simple example of streaming audio using gRPC and C# 8 async streams
dkakaie/localtunnel.net
.NET implementation of a tunnel client for localtunnel.me.
dkakaie/milvus-workbench
C# SDK for Milvus.
dkakaie/minituna
A toy hyperparameter optimization framework intended for understanding Optuna's internal design.
dkakaie/MoveToDesktop
Move windows using hotkeys or the system menu
dkakaie/NSmartProxy
NSmartProxy是一款开源的内网穿透工具。采用.NET CORE的全异步模式打造。(NSmartProxy is an open source reverse proxy tool that creates a secure tunnel from a public endpoint to a locally service.)
dkakaie/NumsharpOpencvSharpConvertor
A convertor betwwen Numsharp NdArray and OpenCvSharp Mat
dkakaie/onnxruntime-wav2vec
dkakaie/our-voices-model-competition
Our Voices Competition
dkakaie/tunl
serverless v2ray tunnel
dkakaie/V2ray-for-Doprax
The tool can install v2ray on the Doprax, including VMess and VLess protocols, it will automatically switch IP, you need to fork this projects, read readme.md and run it. Create By ifeng.
dkakaie/vllm-whisper
A high-throughput and memory-efficient inference and serving engine for Whisper, https://mesolitica.com/blog/vllm-whisper
dkakaie/WebRtcVadSharp
.NET Standard interface for the WebRTC voice activity detection (VAD) component.
dkakaie/Whisper
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
dkakaie/whisper-dot-net
Whisper.net are dotnet bindings for whisper.cpp.
dkakaie/whisper-finetuning
Repository contains code to fine-tune WhisperASR model
dkakaie/whisper-finetuning-with-timestamps
[WIP] Scripts for fine-tuning a Whisper model
dkakaie/whisper-multiple-hf-datasets
Whisper fine-tuning event script to use multiple hf datasets
dkakaie/whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
dkakaie/Whisperer
Batch speech to text using OpenAI's whisper.