lyrics-transcriber 0.12.9__py3-none-any.whl → 0.13.1__py3-none-any.whl

lyrics_transcriber/transcriber.py

@@ -190,6 +190,9 @@ class LyricsTranscriber:
             online_lyrics_text_key = f"{online_lyrics_source}_lyrics_text"
             online_lyrics_filepath_key = f"{online_lyrics_source}_lyrics_filepath"
 
+            if online_lyrics_text_key not in self.outputs:
+                continue
+
             data_input_str = (
                 f'Data input 1:\n{self.outputs["transcribed_lyrics_text"]}\nData input 2:\n{self.outputs[online_lyrics_text_key]}\n'
             )
@@ -274,7 +277,7 @@ class LyricsTranscriber:
         total_segments = len(self.outputs["transcription_data_dict"]["segments"])
         self.logger.info(f"Beginning correction using LLM, total segments: {total_segments}")
 
-        with open(self.outputs["llm_transcript_filepath"], "a", buffering=1) as llm_transcript_file:
+        with open(self.outputs["llm_transcript_filepath"], "a", buffering=1, encoding="utf-8") as llm_transcript_file:
             self.logger.debug(f"writing LLM chat instructions: {self.outputs['llm_transcript_filepath']}")
 
             llm_transcript_header = f"--- SYSTEM instructions passed in for all segments ---:\n\n{system_prompt}\n"
@@ -370,7 +373,7 @@ class LyricsTranscriber:
             self.logger.info(f'Successfully processed correction for all {len(corrected_lyrics_dict["segments"])} lyrics segments')
 
             self.logger.debug(f"writing corrected lyrics data JSON filepath: {corrected_lyrics_data_json_cache_filepath}")
-            with open(corrected_lyrics_data_json_cache_filepath, "w") as corrected_lyrics_data_json_cache_file:
+            with open(corrected_lyrics_data_json_cache_filepath, "w", encoding="utf-8") as corrected_lyrics_data_json_cache_file:
                 corrected_lyrics_data_json_cache_file.write(json.dumps(corrected_lyrics_dict, indent=4))
 
         self.outputs["corrected_lyrics_data_filepath"] = corrected_lyrics_data_json_cache_filepath
@@ -405,7 +408,7 @@ class LyricsTranscriber:
             self.outputs["corrected_lyrics_text"] = ""
 
             self.logger.debug(f"writing lyrics plain text to corrected_lyrics_text_filepath: {corrected_lyrics_text_filepath}")
-            with open(corrected_lyrics_text_filepath, "w") as f:
+            with open(corrected_lyrics_text_filepath, "w", encoding="utf-8") as f:
                 for corrected_segment in self.outputs["corrected_lyrics_data_dict"]["segments"]:
                     self.outputs["corrected_lyrics_text"] += corrected_segment["text"].strip() + "\n"
                     f.write(corrected_segment["text".strip()] + "\n")
@@ -452,7 +455,7 @@ class LyricsTranscriber:
             self.logger.debug(
                 f"writing lyrics data JSON to spotify_lyrics_data_json_cache_filepath: {spotify_lyrics_data_json_cache_filepath}"
             )
-            with open(spotify_lyrics_data_json_cache_filepath, "w") as f:
+            with open(spotify_lyrics_data_json_cache_filepath, "w", encoding="utf-8") as f:
                 f.write(spotify_lyrics_json)
         except Exception as e:
             self.logger.warn(f"caught exception while attempting to fetch from spotify: ", e)
@@ -472,7 +475,7 @@ class LyricsTranscriber:
             self.outputs["spotify_lyrics_text"] = ""
 
             self.logger.debug(f"writing lyrics plain text to spotify_lyrics_text_filepath: {spotify_lyrics_text_filepath}")
-            with open(spotify_lyrics_text_filepath, "w") as f:
+            with open(spotify_lyrics_text_filepath, "w", encoding="utf-8") as f:
                 for line in lines:
                     self.outputs["spotify_lyrics_text"] += line["words"].strip() + "\n"
                     f.write(line["words"].strip() + "\n")
@@ -504,7 +507,7 @@ class LyricsTranscriber:
         lyrics = self.clean_genius_lyrics(song.lyrics)
 
         self.logger.debug(f"writing clean lyrics to genius_lyrics_cache_filepath: {genius_lyrics_cache_filepath}")
-        with open(genius_lyrics_cache_filepath, "w") as f:
+        with open(genius_lyrics_cache_filepath, "w", encoding="utf-8") as f:
             f.write(lyrics)
 
         self.outputs["genius_lyrics_filepath"] = genius_lyrics_cache_filepath
@@ -558,7 +561,7 @@ class LyricsTranscriber:
 
         lrc_filename = self.outputs["midico_lrc_filepath"]
         self.logger.debug(f"writing midico formatted word timestamps to LRC file: {lrc_filename}")
-        with open(lrc_filename, "w") as f:
+        with open(lrc_filename, "w", encoding="utf-8") as f:
             f.write("[re:MidiCo]\n")
             for segment in self.outputs["corrected_lyrics_data_dict"]["segments"]:
                 for i, word in enumerate(segment["words"]):
@@ -752,7 +755,7 @@ class LyricsTranscriber:
             self.outputs["transcribed_lyrics_text"] = ""
 
             self.logger.debug(f"writing lyrics plain text to transcribed_lyrics_text_filepath: {transcribed_lyrics_text_filepath}")
-            with open(transcribed_lyrics_text_filepath, "w") as f:
+            with open(transcribed_lyrics_text_filepath, "w", encoding="utf-8") as f:
                 for segment in self.outputs["transcription_data_dict"]["segments"]:
                     self.outputs["transcribed_lyrics_text"] += segment["text"] + "\n"
                     f.write(segment["text"].strip() + "\n")

lyrics_transcriber/utils/cli.py

@@ -2,7 +2,6 @@
 import argparse
 import logging
 import pkg_resources
-from lyrics_transcriber import LyricsTranscriber
 
 
 def main():
@@ -110,6 +109,9 @@ def main():
 
     logger.debug("Loading LyricsTranscriber class")
 
+    # Lazy load this class so help output is printed quickly rather than waiting for heavy libraries to load
+    from lyrics_transcriber import LyricsTranscriber
+
     transcriber = LyricsTranscriber(
         args.audio_filepath,
         genius_api_token=args.genius_api_token,

{lyrics_transcriber-0.12.9.dist-info → lyrics_transcriber-0.13.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lyrics-transcriber
-Version: 0.12.9
+Version: 0.13.1
 Summary: Automatically create synchronised lyrics files in ASS and MidiCo LRC formats with word-level timestamps, using Whisper and lyrics from Genius and Spotify
 Home-page: https://github.com/karaokenerds/python-lyrics-transcriber
 License: MIT
@@ -13,21 +13,22 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: Cython (>=0,<1)
-Requires-Dist: dtw-python (>=1,<2)
-Requires-Dist: llvmlite (>=0,<1)
-Requires-Dist: lyricsgenius (>=3,<4)
-Requires-Dist: numba (>=0.57,<0.58)
-Requires-Dist: numpy (>=1,<2)
-Requires-Dist: onnx (>=1,<2)
-Requires-Dist: onnxruntime (>=1,<2)
+Requires-Dist: Cython (>=0)
+Requires-Dist: dtw-python (>=1)
+Requires-Dist: llvmlite (>=0)
+Requires-Dist: lyricsgenius (>=3)
+Requires-Dist: numba (>=0.57)
+Requires-Dist: numpy (>=1)
+Requires-Dist: onnx (>=1)
+Requires-Dist: onnxruntime (>=1)
 Requires-Dist: openai (>=1,<2)
-Requires-Dist: openai-whisper (==20231117)
-Requires-Dist: python-slugify (>=8,<9)
-Requires-Dist: syrics (>=0,<1)
-Requires-Dist: torch (>1)
-Requires-Dist: tqdm (>=4,<5)
-Requires-Dist: whisper-timestamped (>=1,<2)
+Requires-Dist: openai-whisper (>=20231117)
+Requires-Dist: python-slugify (>=8)
+Requires-Dist: syrics (>=0)
+Requires-Dist: torch (>=1)
+Requires-Dist: tqdm (>=4)
+Requires-Dist: transformers (>=4)
+Requires-Dist: whisper-timestamped (>=1)
 Project-URL: Documentation, https://github.com/karaokenerds/python-lyrics-transcriber/blob/main/README.md
 Project-URL: Repository, https://github.com/karaokenerds/python-lyrics-transcriber
 Description-Content-Type: text/markdown

{lyrics_transcriber-0.12.9.dist-info → lyrics_transcriber-0.13.1.dist-info}/RECORD

@@ -5,13 +5,13 @@ lyrics_transcriber/llm_prompts/llm_prompt_lyrics_correction_gpt_optimised_202311
 lyrics_transcriber/llm_prompts/llm_prompt_lyrics_matching_andrew_handwritten_20231118.txt,sha256=hvk2Vs3M3Q4zGQsiQnXvnpd8wXWfwsudYeqN5qFyNWs,1754
 lyrics_transcriber/llm_prompts/promptfooconfig.yaml,sha256=O4YxlLV7XSUiSw_1Q9G7ELC2VAbrYUV_N5QxrPbd1jE,3735
 lyrics_transcriber/llm_prompts/test_data/ABBA-UnderAttack-Genius.txt,sha256=8d-RvZtyINKUlpQLwMi-VD--Y59J-epPt7SZSqjFbPI,1690
-lyrics_transcriber/transcriber.py,sha256=ykodPGx-bDmT3BBGY5MywfMfmUGUrUsQw7C-k-PzYS0,38686
+lyrics_transcriber/transcriber.py,sha256=YrDx8OhVV6UUljuDic4DmBsQnkalH-iBUFX2Svl7L1U,38915
 lyrics_transcriber/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lyrics_transcriber/utils/ass.py,sha256=b8lnjgXGD1OD1ld_b1xxUmSOf4nSEfz9BpgSkh16R4g,90291
-lyrics_transcriber/utils/cli.py,sha256=-xzokp8RZMh8DDCr-PZbh4yHqlnJP70Ts62-VnjZq48,6398
+lyrics_transcriber/utils/cli.py,sha256=RaZieUW9NuajCq3nU5IvBa-NgFCQ27wraUgrKqOfe7M,6512
 lyrics_transcriber/utils/subtitles.py,sha256=GPLbo9oX3WJIY4wRO40k0RZF-UqvKjr2LFnXVOS0RHI,10762
-lyrics_transcriber-0.12.9.dist-info/LICENSE,sha256=BiPihPDxhxIPEx6yAxVfAljD5Bhm_XG2teCbPEj_m0Y,1069
-lyrics_transcriber-0.12.9.dist-info/METADATA,sha256=et_XjNqSkHONMdJ8KlO9olAK3KkAQ4Wz7HIR8rw0YP0,5051
-lyrics_transcriber-0.12.9.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-lyrics_transcriber-0.12.9.dist-info/entry_points.txt,sha256=lh6L-iR5CGELaNcouDK94X78eS5Ua_tK9lI4UEkza-k,72
-lyrics_transcriber-0.12.9.dist-info/RECORD,,
+lyrics_transcriber-0.13.1.dist-info/LICENSE,sha256=BiPihPDxhxIPEx6yAxVfAljD5Bhm_XG2teCbPEj_m0Y,1069
+lyrics_transcriber-0.13.1.dist-info/METADATA,sha256=j426j7GVyhXPl0kb26Zs6LXYJovCunPRW8iH1YFX0Q0,5047
+lyrics_transcriber-0.13.1.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+lyrics_transcriber-0.13.1.dist-info/entry_points.txt,sha256=lh6L-iR5CGELaNcouDK94X78eS5Ua_tK9lI4UEkza-k,72
+lyrics_transcriber-0.13.1.dist-info/RECORD,,