diff --git a/Cargo.lock b/Cargo.lock index 3e109e3..5662b2d 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -2991,7 +2991,7 @@ dependencies = [ [[package]] name = "parrot" -version = "0.1.6" +version = "0.2.0" dependencies = [ "anyhow", "chrono", diff --git a/native-core/macos/Sources/WhisperCppBridge/WhisperCppBridge.swift b/native-core/macos/Sources/WhisperCppBridge/WhisperCppBridge.swift index 4f88c64..e8a3dcb 100644 --- a/native-core/macos/Sources/WhisperCppBridge/WhisperCppBridge.swift +++ b/native-core/macos/Sources/WhisperCppBridge/WhisperCppBridge.swift @@ -56,6 +56,8 @@ public final class WhisperCppSpeechModel { params.n_threads = Int32(ProcessInfo.processInfo.processorCount) params.no_context = true params.no_timestamps = true + params.suppress_blank = true + params.suppress_nst = true params.print_progress = false params.print_realtime = false params.print_timestamps = false diff --git a/native-core/shared/prompts/cleanup-default-instructions.md b/native-core/shared/prompts/cleanup-default-instructions.md index a055219..8d9da9c 100644 --- a/native-core/shared/prompts/cleanup-default-instructions.md +++ b/native-core/shared/prompts/cleanup-default-instructions.md @@ -11,3 +11,7 @@ Clean the dictated transcript into polished written text. 3. Add natural punctuation and capitalization. Preserve the speaker's meaning, wording, and tone otherwise. Input: can you remind me to call Sarah tomorrow Output: Can you remind me to call Sarah tomorrow? + +4. Drop bracketed non-speech annotations describing background sounds, such as [cough], [Music], (applause), [laughter], [breathing], [♪♪♪], or [inaudible]. Leave brackets that the speaker actually meant (UI labels, citations, parentheticals) alone. + Input: I was walking home [cough] when I saw it. + Output: I was walking home when I saw it. diff --git a/native-core/windows/src/model_whisper_cpp.rs b/native-core/windows/src/model_whisper_cpp.rs index d5a2094..3561483 100644 --- a/native-core/windows/src/model_whisper_cpp.rs +++ b/native-core/windows/src/model_whisper_cpp.rs @@ -87,6 +87,8 @@ impl WhisperCppPipeline { params.set_translate(false); params.set_no_context(true); params.set_no_timestamps(true); + params.set_suppress_blank(true); + params.set_suppress_nst(true); params.set_print_special(false); params.set_print_progress(false); params.set_print_realtime(false);