From 97120a865834a5b1d44a1e98ffb1aae6e29fede9 Mon Sep 17 00:00:00 2001 From: Alex-Wengg Date: Sat, 11 Apr 2026 11:16:48 -0400 Subject: [PATCH] docs: Clarify online vs offline diarization pipeline versions Distinguish between the two diarization pipelines: - Online/streaming (DiarizerManager): Pyannote 3.1 - Offline batch (OfflineDiarizerManager): Pyannote Community-1 Updated documentation: - mobius/getting-started.mdx: Updated model table to show both versions - diarization/streaming.mdx: Added Pyannote 3.1 reference to overview - diarization/getting-started.mdx: Added version note to Quick Start Addresses PR #6 review comment: https://github.com/FluidInference/docs.fluidinference.com/pull/6#discussion_r3068126335 --- diarization/getting-started.mdx | 2 ++ diarization/streaming.mdx | 2 +- mobius/getting-started.mdx | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/diarization/getting-started.mdx b/diarization/getting-started.mdx index 84b3fa8..4bc798a 100644 --- a/diarization/getting-started.mdx +++ b/diarization/getting-started.mdx @@ -11,6 +11,8 @@ description: Speaker diarization — identify who spoke when in audio. ## Quick Start +Pyannote 3.1 online/streaming pipeline: + ```swift import FluidAudio diff --git a/diarization/streaming.mdx b/diarization/streaming.mdx index f7fd3e5..fb911a7 100644 --- a/diarization/streaming.mdx +++ b/diarization/streaming.mdx @@ -5,7 +5,7 @@ description: Real-time speaker diarization for live audio streams. ## Overview -Process audio in chunks for real-time speaker labeling. Use this when you need speaker labels while transcription is happening. For most use cases, the [offline pipeline](/diarization/offline-pipeline) is more accurate. +Pyannote 3.1 pipeline for online/streaming diarization. Process audio in chunks for real-time speaker labeling. Use this when you need speaker labels while transcription is happening. For most use cases, the [offline pipeline](/diarization/offline-pipeline) is more accurate. ## Quick Start diff --git a/mobius/getting-started.mdx b/mobius/getting-started.mdx index febbc2f..0118ae1 100644 --- a/mobius/getting-started.mdx +++ b/mobius/getting-started.mdx @@ -54,7 +54,7 @@ These models have been converted and published to [Hugging Face](https://hugging | **STT** | Parakeet TDT v2 0.6B | [NVIDIA](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) | [FluidInference](https://huggingface.co/FluidInference/parakeet-tdt-0.6b-v2-coreml) | | **STT** | Parakeet EOU 120M | [NVIDIA](https://huggingface.co/nvidia/parakeet-tdt_ctc-110m) | [FluidInference](https://huggingface.co/FluidInference/parakeet-eou-120m-coreml) | | **VAD** | Silero VAD v6 | [Silero](https://github.com/snakers4/silero-vad) | [FluidInference](https://huggingface.co/FluidInference/silero-vad-coreml) | -| **Diarization** | Pyannote Community 1 | [Pyannote](https://huggingface.co/pyannote/speaker-diarization-community-1) | [FluidInference](https://huggingface.co/FluidInference/speaker-diarization-coreml) | +| **Diarization** | Pyannote 3.1 (online) + Community-1 (offline) | [Pyannote 3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) / [Community-1](https://huggingface.co/pyannote/speaker-diarization-community-1) | [FluidInference](https://huggingface.co/FluidInference/speaker-diarization-coreml) | | **TTS** | Kokoro 82M | [Hexgrad](https://huggingface.co/hexgrad/Kokoro-82M) | [FluidInference](https://huggingface.co/FluidInference/kokoro-82m-coreml) | | **TTS** | PocketTTS 155M | [Kyutai](https://huggingface.co/kyutai/pocket-tts) | [FluidInference](https://huggingface.co/FluidInference/pocket-tts-coreml) | | **Embedding** | CAM++ | [3D-Speaker](https://github.com/alibaba-damo-academy/3D-Speaker) | [FluidInference](https://huggingface.co/FluidInference/cam-plusplus-coreml) |