WhisperX Tiny is a fast and accurate speech recognition model with speaker diarization capabilities. Built on OpenAI's Whisper with additional features for alignment and speaker segmentation.
Links
Tags
Repository: localaiLicense: openmdw-1.1
Nemotron-3-Diarization (Sortformer), Q8_0 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo). Speaker diarization only: served through /v1/audio/diarization, returns per-segment start, end and speaker label ("0", "1", ...). It does not transcribe; pair it with an ASR model and set asr_model to get speaker-attributed text from the same call. num_speakers, min_speakers, max_speakers and clustering_threshold are not supported by Sortformer and are ignored.
Links
Tags
Repository: localaiLicense: openmdw-1.1
Nemotron-3-Diarization (Sortformer) paired with the Parakeet TDT+CTC 110M ASR model through the asr_model option, both Q8_0/F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo). Served through /v1/audio/diarization with include_text: each speaker segment comes back with its transcribed text in one call. Diarization model is OpenMDW-1.1, ASR model is CC-BY-4.0.
Links
Tags
Repository: localaiLicense: openmdw-1.1
Nemotron-3-Diarization (Sortformer) with WeSpeaker ResNet34 speaker identification, for the parakeet-cpp backend. Speakers you register with /v1/voice/register (using the voice-detect-wespeaker-resnet34 model) come back by name in /v1/audio/diarization, next to the SPEAKER_NN label. Speakers that are not registered keep only their SPEAKER_NN label. The diarization model is OpenMDW-1.1, the speaker model is CC-BY-4.0. Naming was measured on one two-voice fixture only; check the threshold on your own audio.
Links
Tags
Repository: localaiLicense: openmdw-1.1
Nemotron-3-Diarization (Sortformer) paired with the Parakeet TDT+CTC 110M ASR model through the asr_model option, both Q8_0/F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo). Served through /v1/audio/diarization with include_text: each speaker segment comes back with its transcribed text in one call. Diarization model is OpenMDW-1.1, ASR model is CC-BY-4.0. Also loads WeSpeaker ResNet34 (CC-BY-4.0) through the speaker_model option: speakers registered with /v1/voice/register (voice-detect-wespeaker-resnet34 model) come back by name, next to the SPEAKER_NN label.
Links
Tags
Repository: localaiLicense: cc-by-nc-4.0
Sortformer Diarization 4-speaker v1 (audio.cpp, Q8_0) - speaker diarization for up to four speakers, served by the audio-cpp backend through /v1/audio/diarization. Returns per-segment start, end and speaker label; it does not transcribe, so pair it with an ASR model for text. Q8_0 because upstream records it as a clean Pass, the same as 16-bit, at two thirds of the size. Licensing: the base checkpoint nvidia/diar_sortformer_4spk-v1 is CC BY-NC 4.0, so commercial use is not permitted.
Links
Tags
Repository: localaiLicense: cc-by-4.0
Streaming Sortformer Diarization 4-speaker v2 (nemo-speech-cpp, Q8_0) - speaker diarization for up to four speakers, served by the nemo-speech-cpp backend through /v1/audio/diarization. Returns per-segment start, end and speaker label; it does not transcribe, so pair it with an ASR model for text. This is the streaming variant: use it when you cannot wait for the full recording. For offline batch work the non-streaming v1 is faster and more accurate.
Links
Tags
Repository: localaiLicense: openmdw-1.1
Nemotron 3.5 ASR Streaming 0.6B with streaming Sortformer Diarization 4-speaker v2 (nemo-speech-cpp, Q8_0). Multilingual streaming ASR with per-word speaker tags: the ASR model transcribes and the attached sortformer model labels each word with its speaker. Served through /v1/audio/transcriptions; segments are cut at each speaker change. Q8_0 for both models. The diarization model is the streaming v2 variant, for use when you cannot wait for the full recording.
Links
Tags
Repository: localaiLicense: cc-by-4.0
Parakeet TDT 0.6B v3 with streaming Sortformer Diarization 4-speaker v2 (nemo-speech-cpp, Q8_0). Multilingual streaming ASR with per-word speaker tags: the ASR model transcribes and the attached sortformer model labels each word with its speaker. Served through /v1/audio/transcriptions; segments are cut at each speaker change. Q8_0 for both models. The diarization model is the streaming v2 variant, for use when you cannot wait for the full recording.
Links
Tags