TransWithAI/Faster-Whisper-TransWithAI-ChickenRice

Health v2 · maintenance only

Adoption not part of the score

2196 stars · 99 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A high-performance audio/video transcription and translation application built on Faster Whisper, optimized for Japanese-to-Chinese translation using a custom CTranslate2 model and a voice-optimized VAD model. It supports NVIDIA CUDA and AMD ROCm/HIP GPUs, cloud inference via Modal, and outputs subtitles in SRT, VTT, and LRC formats.

Use cases

• transcribe japanese audio to text
• translate japanese audio to chinese subtitles
• generate srt subtitles from video files
• batch transcribe asmr audio files
• run whisper transcription on amd gpu
• transcribe audio in the cloud without a local gpu

When to choose

• you need Japanese-to-Chinese speech translation with a domain-tuned model
• you want GPU-accelerated batch transcription with subtitle output
• you work with ASMR/voice-heavy audio needing specialized VAD
• you lack a local GPU and want cloud inference via Modal

When to avoid

• you need general multilingual transcription beyond Japanese/Chinese
• you need a lightweight CPU-only transcription tool
• you want a GUI application rather than script/bat-based workflows
• you need real-time streaming transcription

Facets

application · maturity active

speech-recognition machine-learning llm-inference audio-processing video-processing speech-processing media artificial-intelligence windows python cross-platform faster-whisper japanese-to-chinese-translation subtitle-generation vad ctranslate2 gpu-acceleration modal-cloud srt batch-transcription natural-language-processing localization gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="TransWithAI/Faster-Whisper-TransWithAI-ChickenRice")