AG4/project_whispertrans_code
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update: Applied Black formatting

Browse Source
This commit is contained in:
Orihara Izaya
2023-10-09 15:56:25 +02:00
parent f92830facc
commit dc2ee55c4a
5 changed files with 48 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/__init__.py
+1 -1
View File
@@ -1 +1 @@
"""Functions to get video data and create transcripts as well as detailed information"""
"""Functions to get video data and create transcripts as well as detailed information"""
src/file_manager.py
+9 -3
View File
@@ -23,7 +23,9 @@ class FileManager:
try:
yt = YouTube(youtube_link)
except pytube_exceptions.PytubeError as e:
logging.error("An Error occurred while fetching the YouTube video: " + str(e))
logging.error(
"An Error occurred while fetching the YouTube video: " + str(e)
)
return
audio_stream = yt.streams.get_audio_only()
@@ -33,7 +35,9 @@ class FileManager:
audio_stream.download(filename=filename)
logging.info(f"Downloaded {youtube_link} successfully.")
except Exception as e:
logging.error("An Error occurred while downloading the YouTube video: " + str(e))
logging.error(
"An Error occurred while downloading the YouTube video: " + str(e)
)
return
@staticmethod
@@ -61,7 +65,9 @@ class FileManager:
audio = AudioSegment.from_file(local_file_path, format=ext[1:])
audio.export(wav_file, format="wav")
except Exception as e:
logging.error(f"An error occurred while converting {local_file_path} to wav: {e}")
logging.error(
f"An error occurred while converting {local_file_path} to wav: {e}"
)
return wav_file
src/main.py
+3 -5
View File
@@ -5,14 +5,12 @@ from src.transcript_generator import TranscriptGenerator
def main():
# input could be a YouTube link or a local file
input_sources = [
'https://www.youtube.com/watch?v=BVVo1BaL6JA'
]
input_sources = ["https://www.youtube.com/watch?v=BVVo1BaL6JA"]
hf_token = os.environ.get('HF_TOKEN')
hf_token = os.environ.get("HF_TOKEN")
if not hf_token:
hf_token = input("Please enter your HF_TOKEN: ")
os.environ['HF_TOKEN'] = hf_token
os.environ["HF_TOKEN"] = hf_token
transcript_generator = TranscriptGenerator()
transcript_generator.generate(input_sources)
src/transcriber.py
+28 -13
View File
@@ -14,7 +14,12 @@ logger = logging.getLogger(__name__)
class Transcriber:
"""A class to transcribe audio files using whisperx."""
def __init__(self, language_code: str = "en", device: str = "cuda", compute_type: str = "float16"):
def __init__(
self,
language_code: str = "en",
device: str = "cuda",
compute_type: str = "float16",
):
"""
Init method.
:param language_code: str: Language code for whisperx transcription (default is "en").
@@ -24,14 +29,17 @@ class Transcriber:
self.device = device if torch.cuda.is_available() else "cpu"
# Initialize the transcription and alignment models
try:
self.transcription_model = whisperx.load_model("large-v2", device=self.device, compute_type=compute_type)
self.alignment_model, self.metadata = whisperx.load_align_model(language_code=language_code,
device=self.device)
self.transcription_model = whisperx.load_model(
"large-v2", device=self.device, compute_type=compute_type
)
self.alignment_model, self.metadata = whisperx.load_align_model(
language_code=language_code, device=self.device
)
except Exception as e:
logger.exception("Failed to initialize models: %s", e)
raise
self.transcript_output = None
self.hf_token = os.environ.get('HF_TOKEN')
self.hf_token = os.environ.get("HF_TOKEN")
def transcribe(self, wav_filename: str, batch_size: int = 16) -> dict:
"""
@@ -48,15 +56,22 @@ class Transcriber:
result = self.transcription_model.transcribe(audio, batch_size=batch_size)
# Use the alignment model
result = whisperx.align(result["segments"], self.alignment_model, self.metadata, audio, self.device,
return_char_alignments=False)
result = whisperx.align(
result["segments"],
self.alignment_model,
self.metadata,
audio,
self.device,
return_char_alignments=False,
)
# Clear GPU memory
self._clear_memory()
# Run Diarization
diarize_model = whisperx.DiarizationPipeline(use_auth_token=self.hf_token,
device=self.device)
diarize_model = whisperx.DiarizationPipeline(
use_auth_token=self.hf_token, device=self.device
)
diarize_segments = diarize_model(audio)
result = whisperx.assign_word_speakers(diarize_segments, result)
@@ -76,13 +91,13 @@ class Transcriber:
"""
try:
# Save full results to a json file
with open(output_json_file, 'w') as f:
with open(output_json_file, "w") as f:
json.dump(self.transcript_output, f)
# Save just the transcripts to a .txt file
transcripts = [seg['text'] for seg in self.transcript_output['segments']]
with open(output_txt_file, 'w') as f:
f.write('\n'.join(transcripts))
transcripts = [seg["text"] for seg in self.transcript_output["segments"]]
with open(output_txt_file, "w") as f:
f.write("\n".join(transcripts))
except Exception as e:
logger.exception("Failed to save transcript: %s", e)
raise
src/transcript_generator.py
+7 -5
View File
@@ -28,7 +28,7 @@ class TranscriptGenerator:
"""
for i, source in enumerate(input_sources):
try:
if source.startswith('http'):
if source.startswith("http"):
mp4_filename = f"audio_{i + 1}.mp4"
wav_filename = f"audio_{i + 1}.wav"
self.file_manager.download_youtube_audio(source, mp4_filename)
@@ -36,11 +36,13 @@ class TranscriptGenerator:
else:
wav_filename = self.file_manager.load_local_file(source)
self.transcriber.transcribe(wav_filename)
json_output_file = f'result_{i + 1}.json'
txt_output_file = f'transcripts_{i + 1}.txt'
json_output_file = f"result_{i + 1}.json"
txt_output_file = f"transcripts_{i + 1}.txt"
self.transcriber.save_transcript(json_output_file, txt_output_file)
except Exception as e:
logger.exception(f"Failed to generate transcript for source {source}. Error: {str(e)}")
logger.exception(
f"Failed to generate transcript for source {source}. Error: {str(e)}"
)
continue
logger.info('Transcription generation completed.')
logger.info("Transcription generation completed.")