{"data":{"node":{"slug":"jitsi-jiwer","name":"jiwer","tagline":"Evaluate speech-to-text systems with word error rate (WER) measures","github_url":"https://github.com/jitsi/jiwer","owner":"jitsi","repo":"jiwer","owner_avatar_url":"https://avatars.githubusercontent.com/u/3671647?v=4","primary_language":"Python","stars":917,"forks":107,"topics":["automatic-speech-recognition","evaluation-metrics","python3","speech-to-text","wer","word-error-rate"],"archived":false,"github_pushed_at":"2026-04-16T15:04:03+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/jitsi-jiwer","markdown_url":"https://www.graphcanon.com/tools/jitsi-jiwer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jitsi-jiwer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jitsi-jiwer"},"categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"automatic-speech-recognition","name":"automatic-speech-recognition"},{"slug":"evaluation-metrics","name":"evaluation-metrics"},{"slug":"python3","name":"python3"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"wer","name":"wer"},{"slug":"word-error-rate","name":"word-error-rate"}],"edges":[],"neighbours":[{"slug":"m-bain-whisperx","name":"whisperX","tagline":"WhisperX for automatic speech recognition with word-level timestamps and diarization","github_url":"https://github.com/m-bain/whisperX","owner":"m-bain","repo":"whisperX","owner_avatar_url":"https://avatars.githubusercontent.com/u/36994049?v=4","primary_language":"Python","stars":23329,"forks":2361,"topics":["asr","speech","speech-recognition","speech-to-text","whisper"],"archived":false,"github_pushed_at":"2026-07-13T08:30:07+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/m-bain-whisperx","markdown_url":"https://www.graphcanon.com/tools/m-bain-whisperx.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/m-bain-whisperx","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=m-bain-whisperx","shared_categories":[]},{"slug":"modelscope-funasr","name":"FunASR","tagline":"Industrial-grade speech recognition toolkit","github_url":"https://github.com/modelscope/FunASR","owner":"modelscope","repo":"FunASR","owner_avatar_url":"https://avatars.githubusercontent.com/u/109945100?v=4","primary_language":"Python","stars":19554,"forks":1965,"topics":["asr","audio","chinese","emotion-recognition","funasr","mcp-server","multilingual-asr","openai-compatible-api","paraformer","punctuation","pytorch","real-time-asr","speaker-diarization","speech-recognition","speech-to-text","streaming-asr","transcription","vllm","voice-activity-detection","whisper-alternative"],"archived":false,"github_pushed_at":"2026-07-30T01:45:38+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/modelscope-funasr","markdown_url":"https://www.graphcanon.com/tools/modelscope-funasr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/modelscope-funasr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=modelscope-funasr","shared_categories":[]},{"slug":"confident-ai-deepeval","name":"deepeval","tagline":"LLM Evaluation Framework.","github_url":"https://github.com/confident-ai/deepeval","owner":"confident-ai","repo":"deepeval","owner_avatar_url":"https://avatars.githubusercontent.com/u/130858411?v=4","primary_language":"Python","stars":17226,"forks":1736,"topics":["evaluation-framework","evaluation-metrics","llm-evaluation","llm-evaluation-framework","llm-evaluation-metrics","python"],"archived":false,"github_pushed_at":"2026-07-27T11:33:31+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/confident-ai-deepeval","markdown_url":"https://www.graphcanon.com/tools/confident-ai-deepeval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/confident-ai-deepeval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=confident-ai-deepeval","shared_categories":["evaluation-observability"]},{"slug":"alphacep-vosk-api","name":"vosk-api","tagline":"Offline speech recognition API","github_url":"https://github.com/alphacep/vosk-api","owner":"alphacep","repo":"vosk-api","owner_avatar_url":"https://avatars.githubusercontent.com/u/26358566?v=4","primary_language":"Jupyter Notebook","stars":15013,"forks":1740,"topics":["android","asr","deep-learning","deep-neural-networks","deepspeech","google-speech-to-text","ios","kaldi","offline","privacy","python","raspberry-pi","speaker-identification","speaker-verification","speech-recognition","speech-to-text","speech-to-text-android","stt","voice-recognition","vosk"],"archived":false,"github_pushed_at":"2026-07-02T20:03:34+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/alphacep-vosk-api","markdown_url":"https://www.graphcanon.com/tools/alphacep-vosk-api.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alphacep-vosk-api","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alphacep-vosk-api","shared_categories":[]},{"slug":"eleutherai-lm-evaluation-harness","name":"lm-evaluation-harness","tagline":"A framework for few-shot evaluation of language models.","github_url":"https://github.com/EleutherAI/lm-evaluation-harness","owner":"EleutherAI","repo":"lm-evaluation-harness","owner_avatar_url":"https://avatars.githubusercontent.com/u/68924597?v=4","primary_language":"Python","stars":13560,"forks":3467,"topics":["evaluation-framework","language-model","transformer"],"archived":false,"github_pushed_at":"2026-07-13T20:18:15+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/eleutherai-lm-evaluation-harness","markdown_url":"https://www.graphcanon.com/tools/eleutherai-lm-evaluation-harness.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eleutherai-lm-evaluation-harness","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eleutherai-lm-evaluation-harness","shared_categories":["evaluation-observability"]},{"slug":"funaudiollm-sensevoice","name":"SenseVoice","tagline":"Multilingual speech understanding toolkit with ASR, emotion recognition, and audio event detection.","github_url":"https://github.com/FunAudioLLM/SenseVoice","owner":"FunAudioLLM","repo":"SenseVoice","owner_avatar_url":"https://avatars.githubusercontent.com/u/167062371?v=4","primary_language":"C","stars":8961,"forks":799,"topics":["asr","audio-analysis","audio-event-detection","cantonese","cross-lingual","emotion-detection","funasr","language-identification","llama-cpp","multilingual","multilingual-asr","pytorch","sensevoice","speech-emotion-recognition","speech-recognition","speech-to-text","speech-understanding","transcription","voice-ai","whisper-alternative"],"archived":false,"github_pushed_at":"2026-07-27T14:04:29+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/funaudiollm-sensevoice","markdown_url":"https://www.graphcanon.com/tools/funaudiollm-sensevoice.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/funaudiollm-sensevoice","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=funaudiollm-sensevoice","shared_categories":[]},{"slug":"huggingface-speech-to-speech","name":"speech-to-speech","tagline":"Build local voice agents with open-source models","github_url":"https://github.com/huggingface/speech-to-speech","owner":"huggingface","repo":"speech-to-speech","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":8219,"forks":1025,"topics":["ai","assistant","language-model","machine-learning","python","speech","speech-synthesis","speech-to-text","speech-translation"],"archived":false,"github_pushed_at":"2026-07-30T11:35:50+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-speech-to-speech","markdown_url":"https://www.graphcanon.com/tools/huggingface-speech-to-speech.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-speech-to-speech","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-speech-to-speech","shared_categories":[]},{"slug":"sanchit-gandhi-whisper-jax","name":"whisper-jax","tagline":"JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.","github_url":"https://github.com/sanchit-gandhi/whisper-jax","owner":"sanchit-gandhi","repo":"whisper-jax","owner_avatar_url":"https://avatars.githubusercontent.com/u/93869735?v=4","primary_language":"Jupyter Notebook","stars":4684,"forks":411,"topics":["deep-learning","jax","speech-recognition","speech-to-text","whisper"],"archived":false,"github_pushed_at":"2024-04-03T12:12:52+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/sanchit-gandhi-whisper-jax","markdown_url":"https://www.graphcanon.com/tools/sanchit-gandhi-whisper-jax.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sanchit-gandhi-whisper-jax","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sanchit-gandhi-whisper-jax","shared_categories":[]},{"slug":"evolvinglmms-lab-lmms-eval","name":"lmms-eval","tagline":"One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks","github_url":"https://github.com/EvolvingLMMs-Lab/lmms-eval","owner":"EvolvingLMMs-Lab","repo":"lmms-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/154951679?v=4","primary_language":"Python","stars":4368,"forks":639,"topics":["agi","audio-evaluation","benchmark","evaluation","large-language-models","llm-evaluation","multimodal","multimodal-evaluation","video-understanding","vision-language-model","vlm"],"archived":false,"github_pushed_at":"2026-08-06T02:22:23+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval","markdown_url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evolvinglmms-lab-lmms-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evolvinglmms-lab-lmms-eval","shared_categories":["evaluation-observability"]},{"slug":"ahmetoner-whisper-asr-webservice","name":"whisper-asr-webservice","tagline":"OpenAI Whisper ASR Webservice API","github_url":"https://github.com/ahmetoner/whisper-asr-webservice","owner":"ahmetoner","repo":"whisper-asr-webservice","owner_avatar_url":"https://avatars.githubusercontent.com/u/3612657?v=4","primary_language":"Python","stars":3311,"forks":580,"topics":["asr","automatic-speech-recognition","docker","openai-whisper","speech","speech-recognition","speech-to-text"],"archived":false,"github_pushed_at":"2025-11-23T20:52:04+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/ahmetoner-whisper-asr-webservice","markdown_url":"https://www.graphcanon.com/tools/ahmetoner-whisper-asr-webservice.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ahmetoner-whisper-asr-webservice","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ahmetoner-whisper-asr-webservice","shared_categories":[]},{"slug":"linto-ai-whisper-timestamped","name":"whisper-timestamped","tagline":"Multilingual Automatic Speech Recognition with word-level timestamps and confidence","github_url":"https://github.com/linto-ai/whisper-timestamped","owner":"linto-ai","repo":"whisper-timestamped","owner_avatar_url":"https://avatars.githubusercontent.com/u/36000254?v=4","primary_language":"Python","stars":2832,"forks":212,"topics":["asr","attention-is-all-you-need","attention-mechanism","attention-model","attention-network","attention-seq2seq","attention-visualization","deep-learning","machine-learning","multilingual-models","python","python3","pytorch","speaker-diarization","speech","speech-processing","speech-recognition","speech-to-text","transformers","whisper"],"archived":false,"github_pushed_at":"2025-09-09T07:04:36+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/linto-ai-whisper-timestamped","markdown_url":"https://www.graphcanon.com/tools/linto-ai-whisper-timestamped.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/linto-ai-whisper-timestamped","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=linto-ai-whisper-timestamped","shared_categories":[]},{"slug":"fluidinference-fluidaudio","name":"FluidAudio","tagline":"CoreML audio models for text-to-speech, speech-to-text, voice activity detection and speaker diarization in Swift.","github_url":"https://github.com/FluidInference/FluidAudio","owner":"FluidInference","repo":"FluidAudio","owner_avatar_url":"https://avatars.githubusercontent.com/u/216957621?v=4","primary_language":"Swift","stars":2554,"forks":360,"topics":["ane","asr","audio","automatic-speech-recognition","avfoundation","coreml","ios","macos","nvidia","parakeet","real-time","speaker-diarization","speaker-embedding","speaker-identification","speaker-recognition","speech-to-text","swift","vad","voice-activity-detection"],"archived":false,"github_pushed_at":"2026-07-26T00:49:55+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/fluidinference-fluidaudio","markdown_url":"https://www.graphcanon.com/tools/fluidinference-fluidaudio.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fluidinference-fluidaudio","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fluidinference-fluidaudio","shared_categories":[]}]}}