Fix: pipeline.instantiate() modifies in-place, use pipeline directly after instantiate 81c336f Running Thanh-Lam commited on Dec 11, 2025
Fix pipeline instantiation: properly handle default_parameters and instantiate 71155dc Thanh-Lam commited on Dec 11, 2025
Add clear error message about all required gated models that need terms acceptance b503b1d Thanh-Lam commited on Dec 11, 2025
Upgrade to pyannote.audio 3.3.2 and add better error handling for gated models e169a58 Thanh-Lam commited on Dec 11, 2025
Switch to pyannote/speaker-diarization (latest) to avoid deprecated plda parameter 88a86dd Thanh-Lam commited on Dec 11, 2025
Improve plda workaround: instantiate SpeakerDiarization class directly with cleaned params 29d2dcb Thanh-Lam commited on Dec 11, 2025
Add workaround for deprecated plda parameter in model config, downgrade to pyannote.audio 3.0.1 c2b3996 Thanh-Lam commited on Dec 11, 2025
Pin pyannote.audio to 3.1.1 for compatibility with speaker-diarization-3.1 model 419fa8b Thanh-Lam commited on Dec 11, 2025
Fix Pipeline.from_pretrained() to support both token and use_auth_token parameters d2997d8 Thanh-Lam commited on Dec 11, 2025
Add HF_TOKEN env support and improve network error messages for HF Spaces 56dc9d8 Thanh-Lam commited on Dec 11, 2025
