Whispercpp v1.8.4 api

.gitignore

@@ -7,7 +7,15 @@ _generate/
 *.py[cod]
 *.egg-info
 *env*
+# install -e artifacts
 _version.py
+libggml*
+libwhisper*
+
+# ignore downloaded source code... really this is just for quickly checking previous versions
+pywhispercpp-*.*
+
+
 
 # custom
 .idea

README.md

@@ -292,7 +292,10 @@ options:
 ```python
 import _pywhispercpp as pwcpp
 
-ctx = pwcpp.whisper_init_from_file('path/to/ggml/model')
+ctx = pwcpp.whisper_init_from_file_with_params(
+  'path/to/ggml/model',
+  pwcpp.whisper_context_default_params(),
+)
 ```
 
 # Discussions and contributions
@@ -302,4 +305,4 @@ If you have any feedback, or you want to share how you are using this project, f
 
 # License
 
-This project is licensed under the same license as [whisper.cpp](https://github.com/ggerganov/whisper.cpp/blob/master/LICENSE) (MIT  [License](./LICENSE)).
+This project is licensed under the same license as [whisper.cpp](https://github.com/ggerganov/whisper.cpp/blob/master/LICENSE) (MIT  [License](./LICENSE)).

pywhispercpp/constants.py

@@ -95,6 +95,12 @@
             'type': bool,
             'description': "do not use past transcription (if any) as initial prompt for the decoder",
             'options': None,
+            'default': True
+    },
+    'no_timestamps': {
+            'type': bool,
+            'description': "do not generate timestamps",
+            'options': None,
             'default': False
     },
     'single_segment': {
@@ -164,12 +170,24 @@
             'options': None,
             'default': 0
     },
+    'debug_mode': {
+            'type': bool,
+            'description': "enable debug mode in whisper.cpp",
+            'options': None,
+            'default': False
+    },
     'audio_ctx': {
             'type': int,
             'description': "overwrite the audio context size (0 = use default)",
             'options': None,
             'default': 0
     },
+    'tdrz_enable': {
+            'type': bool,
+            'description': "enable tinydiarize speaker turn detection",
+            'options': None,
+            'default': False
+    },
     'initial_prompt': {
             'type': str,
             'description': "Initial prompt, these are prepended to any existing text context from a previous call",
@@ -188,12 +206,24 @@
             'options': None,
             'default': 0
     },
+    'carry_initial_prompt': {
+            'type': bool,
+            'description': "always prepend the initial prompt to each decode window",
+            'options': None,
+            'default': False
+    },
     'language': {
             'type': str,
             'description': 'for auto-detection, set to None, "" or "auto"',
             'options': None,
             'default': ""
     },
+    'detect_language': {
+            'type': bool,
+            'description': 'enable automatic language detection during transcription',
+            'options': None,
+            'default': False
+    },
     'suppress_blank': {
             'type': bool,
             'description': 'common decoding parameters',
@@ -206,6 +236,18 @@
             'options': None,
             'default': False
     },
+    'suppress_nst': {
+            'type': bool,
+            'description': 'canonical whisper.cpp name for non-speech token suppression',
+            'options': None,
+            'default': False
+    },
+    'suppress_regex': {
+            'type': str,
+            'description': 'regex pattern used to suppress matching text during decoding',
+            'options': None,
+            'default': ''
+    },
     'temperature': {
             'type': float,
             'description': 'initial decoding temperature',
@@ -252,7 +294,7 @@
             'type': dict,
             'description': 'greedy',
             'options': None,
-            'default': {"best_of": -1}
+            'default': {"best_of": 5}
     },
     'beam_search': {
             'type': dict,
@@ -264,7 +306,7 @@
             'type': bool,
             'description': 'calculate the geometric mean of token probabilities for each segment.',
             'options': None,
-            'default': True
+            'default': False
     },
     'vad': {
         'type': bool,