ttsforge 0.1.0__py3-none-any.whl → 0.1.1__py3-none-any.whl

ttsforge/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.0'
-__version_tuple__ = version_tuple = (0, 1, 0)
+__version__ = version = '0.1.1'
+__version_tuple__ = version_tuple = (0, 1, 1)
 
 __commit_id__ = commit_id = None

ttsforge/cli/commands_conversion.py

@@ -536,17 +536,17 @@ def convert(  # noqa: C901
         pause_clause=(
             pause_clause
             if pause_clause is not None
-            else config.get("pause_clause", 0.25)
+            else config.get("pause_clause", 0.3)
         ),
         pause_sentence=(
             pause_sentence
             if pause_sentence is not None
-            else config.get("pause_sentence", 0.2)
+            else config.get("pause_sentence", 0.5)
         ),
         pause_paragraph=(
             pause_paragraph
             if pause_paragraph is not None
-            else config.get("pause_paragraph", 0.75)
+            else config.get("pause_paragraph", 0.9)
         ),
         pause_variance=(
             pause_variance
@@ -1369,17 +1369,17 @@ def read(  # noqa: C901
         effective_split_mode = config_split_mode
     # Pause settings
     effective_pause_clause = (
-        pause_clause if pause_clause is not None else config.get("pause_clause", 0.25)
+        pause_clause if pause_clause is not None else config.get("pause_clause", 0.3)
     )
     effective_pause_sentence = (
         pause_sentence
         if pause_sentence is not None
-        else config.get("pause_sentence", 0.2)
+        else config.get("pause_sentence", 0.5)
     )
     effective_pause_paragraph = (
         pause_paragraph
         if pause_paragraph is not None
-        else config.get("pause_paragraph", 0.75)
+        else config.get("pause_paragraph", 0.9)
     )
     effective_pause_variance = (
         pause_variance
@@ -1695,7 +1695,6 @@ def read(  # noqa: C901
 
         def generate_audio(text_segment: str) -> tuple[np.ndarray, int]:
             """Generate audio for a text segment."""
-            print(text_segment)
             result = pipeline.run(text_segment)
             return result.audio, result.sample_rate
 

ttsforge/cli/commands_phonemes.py

@@ -603,17 +603,17 @@ def phonemes_convert(
         pause_clause=(
             pause_clause
             if pause_clause is not None
-            else config.get("pause_clause", 0.25)
+            else config.get("pause_clause", 0.3)
         ),
         pause_sentence=(
             pause_sentence
             if pause_sentence is not None
-            else config.get("pause_sentence", 0.2)
+            else config.get("pause_sentence", 0.5)
         ),
         pause_paragraph=(
             pause_paragraph
             if pause_paragraph is not None
-            else config.get("pause_paragraph", 0.75)
+            else config.get("pause_paragraph", 0.9)
         ),
         pause_variance=(
             pause_variance

ttsforge/constants.py

@@ -123,8 +123,8 @@ DEFAULT_CONFIG = {
     "default_split_mode": "auto",
     "default_content_mode": "chapters",  # Content mode for read: chapters or pages
     "default_page_size": 2000,  # Synthetic page size in characters for pages mode
-    "pause_clause": 0.5,
-    "pause_sentence": 0.7,
+    "pause_clause": 0.3,
+    "pause_sentence": 0.5,
     "pause_paragraph": 0.9,
     "pause_variance": 0.05,
     "pause_mode": "auto",  # "tts", "manual", or "auto

ttsforge/conversion.py

@@ -124,9 +124,9 @@ class ConversionState:
     split_mode: str = "auto"
     output_format: str = "m4b"
     silence_between_chapters: float = 2.0
-    pause_clause: float = 0.25
-    pause_sentence: float = 0.2
-    pause_paragraph: float = 0.75
+    pause_clause: float = 0.3
+    pause_sentence: float = 0.5
+    pause_paragraph: float = 0.9
     pause_variance: float = 0.05
     pause_mode: str = "auto"  # "tts", "manual", or "auto
     lang: str | None = None  # Language override for phonemization
@@ -174,11 +174,11 @@ class ConversionState:
 
             # Set defaults for new parameters
             if "pause_clause" not in data:
-                data["pause_clause"] = 0.25
+                data["pause_clause"] = 0.3
             if "pause_sentence" not in data:
-                data["pause_sentence"] = 0.2
+                data["pause_sentence"] = 0.5
             if "pause_paragraph" not in data:
-                data["pause_paragraph"] = 0.75
+                data["pause_paragraph"] = 0.9
             if "pause_variance" not in data:
                 data["pause_variance"] = 0.05
             if "pause_mode" not in data:
@@ -289,9 +289,9 @@ class ConversionOptions:
     phoneme_dictionary_path: str | None = None
     phoneme_dict_case_sensitive: bool = False
     # Pause settings (pykokoro built-in pause handling)
-    pause_clause: float = 0.25  # For clause boundaries (commas)
-    pause_sentence: float = 0.2  # For sentence boundaries
-    pause_paragraph: float = 0.75  # For paragraph boundaries
+    pause_clause: float = 0.3  # For clause boundaries (commas)
+    pause_sentence: float = 0.5  # For sentence boundaries
+    pause_paragraph: float = 0.9  # For paragraph boundaries
     pause_variance: float = 0.05  # Standard deviation for natural variation
     pause_mode: str = "auto"  # "tts", "manual", or "auto
     # Chapter announcement settings

ttsforge/name_extractor.py

@@ -174,7 +174,7 @@ def generate_phoneme_suggestions(
         Dictionary with phoneme suggestions and metadata:
         {
             "name": {
-                "phoneme": "/phoneme/",
+                "phoneme": "phoneme",
                 "occurrences": count,
                 "suggestion_quality": "auto"
             }
@@ -190,7 +190,7 @@ def generate_phoneme_suggestions(
             phoneme = phonemize(name, language=language).phonemes
 
             # Wrap in / / format for dictionary
-            phoneme_formatted = f"/{phoneme}/"
+            phoneme_formatted = f"{phoneme}"
 
             suggestions[name] = {
                 "phoneme": phoneme_formatted,
@@ -201,7 +201,7 @@ def generate_phoneme_suggestions(
             logger.warning(f"Failed to generate phoneme for '{name}': {e}")
             # Add placeholder
             suggestions[name] = {
-                "phoneme": "/FIXME/",
+                "phoneme": "FIXME",
                 "occurrences": count,
                 "suggestion_quality": "error",
                 "error": str(e),

ttsforge/phoneme_conversion.py

@@ -95,9 +95,9 @@ class PhonemeConversionState:
     speed: float = 1.0
     output_format: str = "m4b"
     silence_between_chapters: float = 2.0
-    pause_clause: float = 0.25
-    pause_sentence: float = 0.2
-    pause_paragraph: float = 0.75
+    pause_clause: float = 0.3
+    pause_sentence: float = 0.5
+    pause_paragraph: float = 0.9
     pause_variance: float = 0.05
     pause_mode: str = "auto"
     lang: str | None = None  # Language override for phonemization
@@ -145,11 +145,11 @@ class PhonemeConversionState:
 
             # Set defaults for new parameters
             if "pause_clause" not in data:
-                data["pause_clause"] = 0.25
+                data["pause_clause"] = 0.3
             if "pause_sentence" not in data:
-                data["pause_sentence"] = 0.2
+                data["pause_sentence"] = 0.5
             if "pause_paragraph" not in data:
-                data["pause_paragraph"] = 0.75
+                data["pause_paragraph"] = 0.9
             if "pause_variance" not in data:
                 data["pause_variance"] = 0.05
             if "pause_mode" not in data:
@@ -210,9 +210,9 @@ class PhonemeConversionOptions:
     # If None, language from PhonemeSegments is used
     lang: str | None = None
     # Pause settings (pykokoro built-in pause handling)
-    pause_clause: float = 0.25  # For clause boundaries (commas)
-    pause_sentence: float = 0.2  # For sentence boundaries
-    pause_paragraph: float = 0.75  # For paragraph boundaries
+    pause_clause: float = 0.3  # For clause boundaries (commas)
+    pause_sentence: float = 0.5  # For sentence boundaries
+    pause_paragraph: float = 0.9  # For paragraph boundaries
     pause_variance: float = 0.05  # Standard deviation for natural variation
     pause_mode: str = "auto"  # "tts", "manual", or "auto"
     # Chapter announcement settings

ttsforge/ssmd_generator.py

@@ -2,8 +2,8 @@
 
 This module converts chapter text to SSMD format with markup for:
 - Emphasis (*text* for moderate, **text** for strong)
-- Language switches ([text](lang_code))
-- Phoneme substitutions ([word](ph: /phoneme/))
+- Language switches ([text]{lang="lang_code"})
+- Phoneme substitutions ([word]{ph="phoneme"})
 
 Note: Structural breaks (paragraphs, sentences, clauses) are NOT automatically
 added. The SSMD parser in pykokoro handles sentence detection automatically.
@@ -170,7 +170,7 @@ def _inject_phoneme_substitutions(
         if not phoneme:
             return matched_word
         clean_phoneme = phoneme.strip("/")
-        return f"[{matched_word}](ph: /{clean_phoneme}/)"
+        return f"[{matched_word}]" + "{" + f'ph="{clean_phoneme}"' + "}"
 
     segments: list[str] = []
     last_index = 0
@@ -260,7 +260,7 @@ def _strip_redundant_title(chapter_title: str, chapter_text: str) -> str:
         return chapter_text
 
     trimmed_line = title_pattern.sub("", first_line, count=1).lstrip(
-        " \t:;\-\u2013\u2014"
+        " \t:;-\u2013\u2014"
     )
     if trimmed_line:
         lines[first_idx] = trimmed_line

{ttsforge-0.1.0.dist-info → ttsforge-0.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ttsforge
-Version: 0.1.0
+Version: 0.1.1
 Summary: Generate audiobooks from EPUB files using Kokoro ONNX TTS.
 Author-email: Holger Nahrstaedt <nahrstaedt@gmail.com>
 License: MIT License
@@ -396,14 +396,14 @@ SSMD files use a simple markdown-like syntax:
 **Custom Phonemes**:
 
 ```
-[Hermione](ph: /hɝmˈIni/)    # Override pronunciation
-[API](ph: /ˌeɪpiˈaɪ/)        # Technical terms
+[Hermione]{ph="hɝmˈIni"}    # Override pronunciation
+[API]{ph="ˌeɪpiˈaɪ"}        # Technical terms
 ```
 
 **Language Switching** (planned):
 
 ```
-[Bonjour](fr)    # Mark text as French
+[Bonjour]{lang="fr"}    # Mark text as French
 ```
 
 #### Example SSMD File
@@ -411,7 +411,7 @@ SSMD files use a simple markdown-like syntax:
 ```ssmd
 Chapter One ...p
 
-[Harry](ph: /hæɹi/) Potter was a *highly unusual* boy in many ways. ...s
+[Harry]{ph="hæɹi"} Potter was a *highly unusual* boy in many ways. ...s
 For one thing, he **hated** the summer holidays more than any other
 time of year. ...s For another, he really wanted to do his homework,
 but was forced to do it in secret, in the dead of the night. ...p
@@ -498,12 +498,12 @@ Edit `custom_phonemes.json` to fix any incorrect phonemes. The file format is:
   },
   "entries": {
     "Hermione": {
-      "phoneme": "/hɝmˈIni/",
+      "phoneme": "hɝmˈIni",
       "occurrences": 847,
       "verified": false
     },
     "Kubernetes": {
-      "phoneme": "/kubɚnˈɛtɪs/",
+      "phoneme": "kubɚnˈɛtɪs",
       "occurrences": 12,
       "verified": false
     }
@@ -515,8 +515,8 @@ Or use the simple format:
 
 ```json
 {
-  "Hermione": "/hɝmˈIni/",
-  "Kubernetes": "/kubɚnˈɛtɪs/"
+  "Hermione": "hɝmˈIni",
+  "Kubernetes": "kubɚnˈɛtɪs"
 }
 ```
 
@@ -548,9 +548,9 @@ You can create a dictionary manually without extraction:
 
 ```json
 {
-  "Katniss": "/kætnɪs/",
-  "Peeta": "/pitə/",
-  "Panem": "/pænəm/"
+  "Katniss": "kætnɪs",
+  "Peeta": "pitə",
+  "Panem": "pænəm"
 }
 ```
 

{ttsforge-0.1.0.dist-info → ttsforge-0.1.1.dist-info}/RECORD

@@ -1,27 +1,27 @@
 ttsforge/__init__.py,sha256=Jg8_0vPttTVWrnt4HBqrTOKYfmcgpVpfddSVcU4HKXo,2432
-ttsforge/_version.py,sha256=5jwwVncvCiTnhOedfkzzxmxsggwmTBORdFL_4wq0ZeY,704
+ttsforge/_version.py,sha256=m8HxkqoKGw_wAJtc4ZokpJKNLXqp4zwnNhbnfDtro7w,704
 ttsforge/audio_merge.py,sha256=Tt7o8GBNrkcfiSKycUpWvblj-y4zwlULoX-eCblqYpo,5666
 ttsforge/audio_player.py,sha256=HYc4vv46yDXjVXaWRlj1tUtWLiwNTwbzT6oDfOUB5vA,14351
 ttsforge/chapter_selection.py,sha256=a-XlEO4HMzeUBfhvnh6gQOQmDuM0wMpVCi0pw6oM2hQ,2579
-ttsforge/constants.py,sha256=p_-LfE_u1oT--tzjI5PrHGXd5u9DHM7dcHsfcUgvzvY,5108
-ttsforge/conversion.py,sha256=oZ1FyyyeChb6EoCrVJ-maogXqLq537iUBne5oa_epdw,41629
+ttsforge/constants.py,sha256=Y_u8BanHjZBGiAnc9FVPulVHHGIRYlOJhq74BTtxPYA,5108
+ttsforge/conversion.py,sha256=gz6ePEHjC7Nu1zlPArdsIOZA2rb_EEfJMaV6lA-0V2o,41623
 ttsforge/input_reader.py,sha256=b49SBT-mL4SnR74D8xwyWHC_smPhsJ5jpPAj4QQ5WKo,14068
 ttsforge/kokoro_lang.py,sha256=8603b5whfk0KzGrNK7pqRjzoH1Ge9TKoX7AMzKsX0sk,376
 ttsforge/kokoro_runner.py,sha256=ZGBx70_rHcfwKiUgywa_3-7d5u-wQ_0pPOukQRuACu0,4390
-ttsforge/name_extractor.py,sha256=vBVp2OT8sdYdbczs0SQdEcZff2sN1sk5URi5gBwJrcE,9584
-ttsforge/phoneme_conversion.py,sha256=so5Iex2lme9tHvZiCysLBAkBH1tp42O8pkibLSrHzh8,38280
+ttsforge/name_extractor.py,sha256=CxxBadCO0Pcoepcj7gZwkfWPMud2oa9477h_lDYWrIA,9578
+ttsforge/phoneme_conversion.py,sha256=nLnFk1uuMMD1Mw4a24zZeZHDHG_4mG3kW1xiOcKM9YA,38274
 ttsforge/phonemes.py,sha256=EUZ1Qr-0rPThRpSeuJQe5Z3J3nz7rX1Xs3Rjjw19qIQ,15517
-ttsforge/ssmd_generator.py,sha256=Dmuvy6T8WVyzHvaNWsPDdyyTIZCpyX2pOsaVUPk8s08,13326
+ttsforge/ssmd_generator.py,sha256=LknVBSETKH9cY4CoAUBjd1vEfr5VXi0xqEKcft2CR8I,13346
 ttsforge/utils.py,sha256=3BiNFyScV3Dy_xhVm2EigpxUb4Z6YwIQPzzxwDzfCzI,24942
 ttsforge/cli/__init__.py,sha256=CTqYeUAJaKV7YTYqcmr7-VxjwJfjLcnPYM2OKyws0Oc,2103
-ttsforge/cli/commands_conversion.py,sha256=H1fX1M52RdSiSnGfIknr-dBGx-MeMaVf5J6rMDVrgWU,63457
-ttsforge/cli/commands_phonemes.py,sha256=_0PQd9_hjOvzkzx2qM5BEG1fNyZYTjKc5nrZZ41HV4k,32373
+ttsforge/cli/commands_conversion.py,sha256=fvbC62gswEb-qpVoU_9S81nFOApH09v9g29nG0HE9X4,63421
+ttsforge/cli/commands_phonemes.py,sha256=Y1_t4jLDuEFVLY6sQC9uwcU9ptt4Y7FrRBRWtkSAF0o,32371
 ttsforge/cli/commands_utility.py,sha256=_8KMUjVYVqp63PH_gjOjS-fw6ZCujaMDXFxoKfUzlko,48013
 ttsforge/cli/helpers.py,sha256=5Co2EvDhYspKhjW2-P3sNxj9MFFgWyTFeqOyJbPy2yA,2697
 ttsforge/vocab/__init__.py,sha256=lMgS0dY9VbOYI20LnPjjqrWcjLIQ1FKkR4-xcXsvrqc,3641
-ttsforge-0.1.0.dist-info/licenses/LICENSE,sha256=9csb1sDNn0HdUPKgOTUwtb4CkvYPcFXHnkxKCS99EWQ,1074
-ttsforge-0.1.0.dist-info/METADATA,sha256=cQJf57NrwNZJUZacAQgnokqO1cnSC_Mi1b7ZWjcZ0no,19577
-ttsforge-0.1.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-ttsforge-0.1.0.dist-info/entry_points.txt,sha256=SrcNdlhQpoUCzPzhVbOmMzATQeV7j7XYl0DPrVjZ-ks,47
-ttsforge-0.1.0.dist-info/top_level.txt,sha256=rNLi-3muicHF8UvZu_FuA2ML_Dz9sVPCjik2E8XnCVk,9
-ttsforge-0.1.0.dist-info/RECORD,,
+ttsforge-0.1.1.dist-info/licenses/LICENSE,sha256=9csb1sDNn0HdUPKgOTUwtb4CkvYPcFXHnkxKCS99EWQ,1074
+ttsforge-0.1.1.dist-info/METADATA,sha256=tVUrSm-pBcKWQ0gyrsazqadW0ufARWPXp00qHJsf6ag,19567
+ttsforge-0.1.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+ttsforge-0.1.1.dist-info/entry_points.txt,sha256=SrcNdlhQpoUCzPzhVbOmMzATQeV7j7XYl0DPrVjZ-ks,47
+ttsforge-0.1.1.dist-info/top_level.txt,sha256=rNLi-3muicHF8UvZu_FuA2ML_Dz9sVPCjik2E8XnCVk,9
+ttsforge-0.1.1.dist-info/RECORD,,