{"skill":{"slug":"gipformer","displayName":"Gipformer ASR","summary":"Vietnamese speech-to-text using Gipformer ASR (65M params, Zipformer-RNNT). Accepts audio of any length — the server handles VAD chunking, batching, and retu...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":191,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774402817697,"updatedAt":1774403817398},"latestVersion":{"version":"1.0.0","createdAt":1774402817697,"changelog":"Initial release of Vietnamese speech-to-text using Gipformer ASR.\n\n- Supports speech recognition for Vietnamese audio using a 65M parameter Zipformer-RNNT model.\n- Accepts audio in WAV, FLAC, OGG, MP3, and M4A formats; any duration.\n- Handles VAD chunking, batching, and provides full transcript with chunk metadata.\n- Server and CLI tools provided for both API and script-based transcription.\n- Configurable for quantization, batch size, decoding method, and format support (ffmpeg required for M4A).\n- Includes health check and comprehensive API documentation.","license":"MIT-0"},"metadata":null,"owner":{"handle":"ai-ggroup","userId":"s17dtfxadcv4k08hyxxrarfwsn83g08f","displayName":"AI-GGroup","image":"https://avatars.githubusercontent.com/u/208556716?v=4"},"moderation":null}