Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-11-23 22:15:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #3 from ariavn-byte/copilot/review-repo-011cv3pvca7zsctw2yquumb8

Browse Source 
Fix critical flake8 violations: unused imports, f-string placeholders, and slice spacing
This commit is contained in:
Arya vaghayenegar 2025-11-16 02:39:36 -05:00 committed by GitHub
commit d93554a9ec
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 5 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
farsi_transcriber/config.py
View File

@ -4,7 +4,6 @@ Configuration settings for Farsi Transcriber application
Manages model selection, device settings, and other configuration options. Manages model selection, device settings, and other configuration options.
""" """
import os
from pathlib import Path from pathlib import Path
# Application metadata # Application metadata

3
farsi_transcriber/models/whisper_transcriber.py
View File

@ -4,7 +4,6 @@ Whisper Transcriber Module
Handles Farsi audio/video transcription using OpenAI's Whisper model. Handles Farsi audio/video transcription using OpenAI's Whisper model.
""" """
import os
import warnings import warnings
from pathlib import Path from pathlib import Path
from typing import Dict, List, Optional from typing import Dict, List, Optional
@ -53,7 +52,7 @@ class FarsiTranscriber:
warnings.simplefilter("ignore") warnings.simplefilter("ignore")
self.model = whisper.load_model(model_name, device=self.device) self.model = whisper.load_model(model_name, device=self.device)
print(f"Model loaded successfully") print("Model loaded successfully")
def transcribe( def transcribe(
self, self,

6
whisper/transcribe.py
View File

@ -281,7 +281,7 @@ def transcribe(
time_offset = float(seek * HOP_LENGTH / SAMPLE_RATE) time_offset = float(seek * HOP_LENGTH / SAMPLE_RATE)
window_end_time = float((seek + N_FRAMES) * HOP_LENGTH / SAMPLE_RATE) window_end_time = float((seek + N_FRAMES) * HOP_LENGTH / SAMPLE_RATE)
segment_size = min(N_FRAMES, content_frames - seek, seek_clip_end - seek) segment_size = min(N_FRAMES, content_frames - seek, seek_clip_end - seek)
mel_segment = mel[:, seek : seek + segment_size] mel_segment = mel[:, seek:seek + segment_size]
segment_duration = segment_size * HOP_LENGTH / SAMPLE_RATE segment_duration = segment_size * HOP_LENGTH / SAMPLE_RATE
mel_segment = pad_or_trim(mel_segment, N_FRAMES).to(model.device).to(dtype) mel_segment = pad_or_trim(mel_segment, N_FRAMES).to(model.device).to(dtype)
@ -444,7 +444,7 @@ def transcribe(
continue continue
if is_segment_anomaly(segment): if is_segment_anomaly(segment):
next_segment = next_words_segment( next_segment = next_words_segment(
current_segments[si + 1 :] current_segments[si + 1:]
) )
if next_segment is not None: if next_segment is not None:
hal_next_start = next_segment["words"][0]["start"] hal_next_start = next_segment["words"][0]["start"]
@ -508,7 +508,7 @@ def transcribe(
pbar.update(min(content_frames, seek) - previous_seek) pbar.update(min(content_frames, seek) - previous_seek)
return dict( return dict(
text=tokenizer.decode(all_tokens[len(initial_prompt_tokens) :]), text=tokenizer.decode(all_tokens[len(initial_prompt_tokens):]),
segments=all_segments, segments=all_segments,
language=language, language=language,
) )

2
whisper/utils.py
View File

@ -153,7 +153,7 @@ class SubtitlesWriter(ResultWriter):
if max_words_per_line > len(segment["words"]) - chunk_index: if max_words_per_line > len(segment["words"]) - chunk_index:
words_count = remaining_words words_count = remaining_words
for i, original_timing in enumerate( for i, original_timing in enumerate(
segment["words"][chunk_index : chunk_index + words_count] segment["words"][chunk_index:chunk_index + words_count]
): ):
timing = original_timing.copy() timing = original_timing.copy()
long_pause = ( long_pause = (