import gradio as gr import librosa import soundfile import tempfile import os import uuid import json import re from nemo.collections.asr.models import ASRModel from nemo.utils import logging from align import main, AlignmentConfig, ASSFileConfig SAMPLE_RATE = 16000 logging.setLevel(logging.INFO) # --- ASS TO SRT/LRC/ELRC CONVERTER FUNCTIONS --- def format_srt_time(secs): h = int(secs // 3600) m = int((secs % 3600) // 60) s = int(secs % 60) ms = int(round((secs % 1) * 1000)) if ms == 1000: ms = 0 s += 1 return f"{h:02d}:{m:02d}:{s:02d},{ms:03d}" def format_lrc_time(secs): m = int(secs // 60) s = int(secs % 60) cs = int(round((secs % 1) * 100)) if cs == 100: cs = 0 s += 1 return f"{m:02d}:{s:02d}.{cs:02d}" def build_color_map(raw_text): color_map = [] current_color = "default" regex = re.compile(r'(\{[^}]+\})|([^{]+)') for match in regex.finditer(raw_text): tag = match.group(1) text = match.group(2) if tag: c_match = re.search(r'\\c&H([0-9a-fA-F]+)&', tag, re.IGNORECASE) if c_match: current_color = c_match.group(1).lower() elif text: for _ in text: color_map.append(current_color) return color_map def parse_ass_to_segments(text): lines = text.split('\n') dialogues = [] for line in lines: if line.strip().startswith('Dialogue:'): parts = line[10:].split(',') start = parse_ass_time(parts[1]) end = parse_ass_time(parts[2]) raw_text = ','.join(parts[9:]) clean_text_raw = re.sub(r'\{[^}]+\}', '', raw_text) clean_text = re.sub(r'\\N', ' ', clean_text_raw) clean_text = re.sub(r'\s+', ' ', clean_text).strip() dialogues.append({ 'start': start, 'end': end, 'rawText': raw_text, 'cleanTextRaw': clean_text_raw, 'cleanText': clean_text }) segments = [] current_segment = None for d in dialogues: if not current_segment or current_segment['cleanText'] != d['cleanText']: if current_segment: segments.append(current_segment) current_segment = { 'cleanText': d['cleanText'], 'cleanTextRaw': d['cleanTextRaw'], 'startTime': d['start'], 'endTime': d['end'], 'slices': [d] } else: current_segment['slices'].append(d) current_segment['endTime'] = d['end'] if current_segment: segments.append(current_segment) for seg in segments: if not seg['slices']: continue base_color_map = build_color_map(seg['slices'][0]['rawText']) if not base_color_map: seg['words'] = [] continue base_color = base_color_map[-1] words = [] for match in re.finditer(r'\S+', seg['cleanTextRaw']): txt = match.group(0).replace('\\N', '') if txt.strip(): words.append({ 'text': txt, 'startIndex': match.start(), 'isFirstOfSegment': len(words) == 0 }) for w in words: char_pos = w['startIndex'] c0 = base_color_map[char_pos] if char_pos < len(base_color_map) else "default" w_start = seg['startTime'] w_end = seg['endTime'] transitions = [] prev_color = c0 for i in range(1, len(seg['slices'])): slice_d = seg['slices'][i] cmap = build_color_map(slice_d['rawText']) c_curr = cmap[char_pos] if char_pos < len(cmap) else "default" if c_curr != prev_color: transitions.append({'time': slice_d['start'], 'color': c_curr}) prev_color = c_curr if c0 == base_color: w_start = transitions[0]['time'] if len(transitions) > 0 else seg['startTime'] w_end = transitions[1]['time'] if len(transitions) > 1 else seg['endTime'] else: w_start = seg['startTime'] w_end = transitions[0]['time'] if len(transitions) > 0 else seg['endTime'] w['startTime'] = w_start w['endTime'] = w_end if words: words[0]['startTime'] = seg['startTime'] words[-1]['endTime'] = seg['endTime'] seg['words'] = words return segments def generate_srt_segments(segments): out = [] counter = 1 for seg in segments: out.append(str(counter)) out.append(f"{format_srt_time(seg['startTime'])} --> {format_srt_time(seg['endTime'])}") out.append(seg['cleanText']) out.append("") counter += 1 return "\n".join(out).strip() def generate_srt_word_by_word(segments): out = [] counter = 1 for seg in segments: for w in seg['words']: out.append(str(counter)) out.append(f"{format_srt_time(w['startTime'])} --> {format_srt_time(w['endTime'])}") out.append(w['text']) out.append("") counter += 1 return "\n".join(out).strip() def generate_srt_additive(segments): out = [] counter = 1 for seg in segments: accumulated = [] for i, w in enumerate(seg['words']): out.append(str(counter)) actual_start = w['startTime'] if i == 0 else seg['words'][i-1]['endTime'] out.append(f"{format_srt_time(actual_start)} --> {format_srt_time(w['endTime'])}") accumulated.append(w['text']) out.append(" ".join(accumulated)) out.append("") counter += 1 return "\n".join(out).strip() def generate_lrc(segments): out = [] for seg in segments: out.append(f"[{format_lrc_time(seg['startTime'])}]{seg['cleanText']}") out.append(f"[{format_lrc_time(seg['endTime'])}]") return "\n".join(out).strip() def generate_elrc(segments): out = [] for seg in segments: line = f"[{format_lrc_time(seg['startTime'])}]" for i, w in enumerate(seg['words']): if i == 0: line += f"<{format_lrc_time(w['startTime'])}>{w['text']}" else: line += f" <{format_lrc_time(w['startTime'])}>{w['text']}" out.append(line) out.append(f"[{format_lrc_time(seg['endTime'])}]") return "\n".join(out).strip() # --- ORIGINAL PARSING FUNCTIONS --- def parse_srt(content): pattern = re.compile(r'\d+\n(\d{2}:\d{2}:\d{2},\d{3}) --> (\d{2}:\d{2}:\d{2},\d{3})\n((?:(?!\n\n).)*)', re.DOTALL) matches = pattern.findall(content + "\n\n") segments = [] def time_to_sec(t_str): h, m, s_ms = t_str.split(':') s, ms = s_ms.split(',') return int(h) * 3600 + int(m) * 60 + int(s) + int(ms) / 1000.0 for match in matches: start = time_to_sec(match[0]) end = time_to_sec(match[1]) text = match[2].replace('\n', ' ').strip() segments.append({"start": start, "end": end, "text": text}) return segments def parse_lrc(content, audio_duration): lines = content.split('\n') pattern = re.compile(r'\[(\d{2}):(\d{2}\.\d{2,3})\](.*)') raw_markers = [] for line in lines: match = pattern.match(line.strip()) if match: m, s, text = match.groups() start = int(m) * 60 + float(s) raw_markers.append({"start": start, "text": text.strip()}) segments = [] for i in range(len(raw_markers)): current = raw_markers[i] text = current["text"] if text and text != "#": end_time = audio_duration if i + 1 < len(raw_markers): end_time = raw_markers[i+1]["start"] if end_time > current["start"]: segments.append({ "start": current["start"], "end": end_time, "text": text }) return segments def parse_ass_time(t_str): h, m, s = t_str.strip().split(':') return float(h) * 3600 + float(m) * 60 + float(s) def format_ass_time(sec): sec = max(0.0, sec) nh = int(sec // 3600) nm = int((sec % 3600) // 60) ns = sec % 60 return f"{nh:d}:{nm:02d}:{ns:05.2f}" # ----------------------------- def get_audio_data_and_duration(file): data, sr = librosa.load(file) if sr != SAMPLE_RATE: data = librosa.resample(data, orig_sr=sr, target_sr=SAMPLE_RATE) data = librosa.to_mono(data) duration = librosa.get_duration(y=data, sr=SAMPLE_RATE) return data, duration def get_char_tokens(text, model): tokens = [] for character in text: if character in model.decoder.vocabulary: tokens.append(model.decoder.vocabulary.index(character)) else: tokens.append(len(model.decoder.vocabulary)) return tokens def get_S_prime_and_T(text, model_name, model, audio_duration): if "citrinet" in model_name or "_fastconformer_" in model_name: output_timestep_duration = 0.08 elif "_conformer_" in model_name: output_timestep_duration = 0.04 elif "quartznet" in model_name: output_timestep_duration = 0.02 else: raise RuntimeError("unexpected model name") T = int(audio_duration / output_timestep_duration) + 1 if hasattr(model, 'tokenizer'): all_tokens = model.tokenizer.text_to_ids(text) elif hasattr(model.decoder, "vocabulary"): all_tokens = get_char_tokens(text, model) else: raise RuntimeError("cannot obtain tokens from this model") n_token_repetitions = 0 for i_tok in range(1, len(all_tokens)): if all_tokens[i_tok] == all_tokens[i_tok - 1]: n_token_repetitions += 1 S_prime = len(all_tokens) + n_token_repetitions return S_prime, T def delete_mp4s_except_given_filepath(filepath): files_in_dir = os.listdir() mp4_files_in_dir = [x for x in files_in_dir if x.endswith(".mp4")] for mp4_file in mp4_files_in_dir: if mp4_file != filepath: os.remove(mp4_file) def align(Microphone, File_Upload, Video_Upload, subs_file, text, split_on_newline, progress=gr.Progress()): utt_id = uuid.uuid4() output_video_filepath = f"{utt_id}.mp4" delete_mp4s_except_given_filepath(output_video_filepath) output_info = "" ass_text = "" progress(0, desc="Validating input") # FIX: Handle Video upload properly - extract path from tuple if needed video_path = None if Video_Upload is not None: if isinstance(Video_Upload, (tuple, list)): video_path = Video_Upload[0] # First element is the file path elif isinstance(Video_Upload, str): video_path = Video_Upload else: video_path = Video_Upload print(f"Video path extracted: {video_path}") # Ensure only ONE source is used inputs_provided = sum([Microphone is not None, File_Upload is not None, video_path is not None]) if inputs_provided > 1: raise gr.Error("Please use either the microphone, audio file upload, or video upload - not multiple inputs.") elif inputs_provided == 0: raise gr.Error("You have to use the microphone, upload an audio file, or upload a video.") # Process and handle file source extracted_audio_path = None if Microphone is not None: file = Microphone print(f"Using microphone input: {file}") elif File_Upload is not None: file = File_Upload print(f"Using audio file upload: {file}") else: # Step: Extract audio track from video progress(0.05, desc="Extracting audio track from video...") extracted_audio_path = f"extracted_{utt_id}.wav" ffmpeg_extract_cmd = f'ffmpeg -y -i "{video_path}" -vn -acodec pcm_s16le -ar 16000 -ac 1 {extracted_audio_path}' print(f"Running FFmpeg command: {ffmpeg_extract_cmd}") # FIX: Add error checking for FFmpeg result = os.system(ffmpeg_extract_cmd) if result != 0: if os.path.exists(extracted_audio_path): os.remove(extracted_audio_path) raise gr.Error("Failed to extract audio from video. Make sure the video file is valid and FFmpeg is installed.") if not os.path.exists(extracted_audio_path): raise gr.Error("Failed to extract audio from video. No audio file was generated.") file = extracted_audio_path print(f"Audio extracted to: {file}") # FIX: Add validation for audio file try: audio_data, duration = get_audio_data_and_duration(file) print(f"Audio loaded successfully. Duration: {duration:.2f}s") except Exception as e: if extracted_audio_path and os.path.exists(extracted_audio_path): os.remove(extracted_audio_path) raise gr.Error(f"Failed to process audio file: {str(e)}") # Clean up the extracted temporary audio file if created if extracted_audio_path and os.path.exists(extracted_audio_path): os.remove(extracted_audio_path) progress(0.1, desc="Loading speech recognition model") # FIX: Add error handling for model loading try: model_name = "ayymen/stt_zgh_fastconformer_ctc_small" model = ASRModel.from_pretrained(model_name) print(f"Model loaded successfully: {model_name}") except Exception as e: raise gr.Error(f"Failed to load ASR model: {str(e)}") segments = [] if subs_file is not None: progress(0.15, desc="Parsing subtitle file...") # FIX: Handle subs_file properly try: subs_path = subs_file if isinstance(subs_file, str) else subs_file.name print(f"Reading subtitle file: {subs_path}") with open(subs_path, 'r', encoding='utf-8') as f: subs_content = f.read() if subs_path.lower().endswith('.srt'): segments = parse_srt(subs_content) print(f"Parsed {len(segments)} SRT segments") elif subs_path.lower().endswith('.lrc'): segments = parse_lrc(subs_content, duration) print(f"Parsed {len(segments)} LRC segments") else: raise gr.Error("Subtitle file must be an .srt or .lrc file.") if not segments: raise gr.Error("No valid segments found in the subtitle file.") except Exception as e: raise gr.Error(f"Failed to parse subtitle file: {str(e)}") with tempfile.TemporaryDirectory() as tmpdir: manifest_path = os.path.join(tmpdir, f"{utt_id}_manifest.json") if segments: progress(0.2, desc="Chunking audio and generating manifest") print(f"Processing {len(segments)} segments with alignment") with open(manifest_path, 'w', encoding='utf-8') as fout: for i, seg in enumerate(segments): S_prime, T = get_S_prime_and_T(seg['text'], model_name, model, seg['end'] - seg['start']) if S_prime > T: raise gr.Error(f"Segment {i} ('{seg['text']}') has too much text for its audio duration ({seg['end'] - seg['start']:.2f}s).") start_sample = int(seg['start'] * SAMPLE_RATE) end_sample = int(seg['end'] * SAMPLE_RATE) chunk_data = audio_data[start_sample:end_sample] chunk_path = os.path.join(tmpdir, f"{utt_id}_{i:04d}.wav") soundfile.write(chunk_path, chunk_data, SAMPLE_RATE) seg_text = seg['text'].replace('\n', '|') if split_on_newline else seg['text'].replace('\n', ' ') data = { "audio_filepath": chunk_path, "text": seg_text, } fout.write(f"{json.dumps(data)}\n") resegment_text_to_fill_space = False print(f"Manifest created at: {manifest_path}") else: audio_path = os.path.join(tmpdir, f'{utt_id}.wav') soundfile.write(audio_path, audio_data, SAMPLE_RATE) if not text: progress(0.2, desc="Transcribing audio") print("No text provided, running ASR transcription...") text = model.transcribe([audio_path])[0] if 'hybrid' in model_name: text = text[0] if text == "": raise gr.Error("ERROR: the ASR model did not detect any speech. Please upload audio with speech.") output_info += ( "You did not enter any input text, so the ASR model's transcription will be used:\n" "--------------------------\n" f"{text}\n" "--------------------------\n" f"You could try pasting the transcription into the text input box, correcting any" " transcription errors, and clicking 'Submit' again." ) print(f"Transcription: {text}") if split_on_newline: text = "|".join(list(filter(None, text.split("\n")))) S_prime, T = get_S_prime_and_T(text, model_name, model, duration) if S_prime > T: raise gr.Error("The number of tokens in the input text is too long compared to the duration of the audio.") with open(manifest_path, 'w', encoding='utf-8') as fout: data = { "audio_filepath": audio_path, "text": text, } fout.write(f"{json.dumps(data)}\n") resegment_text_to_fill_space = "|" not in text print(f"Manifest created at: {manifest_path}") alignment_config = AlignmentConfig( pretrained_name=model_name, manifest_filepath=manifest_path, output_dir=f"{tmpdir}/nfa_output/", audio_filepath_parts_in_utt_id=1, batch_size=1, use_local_attention=True, additional_segment_grouping_separator="|", save_output_file_formats=["ass", "ctm"], ass_file_config=ASSFileConfig( fontsize=45, resegment_text_to_fill_space=resegment_text_to_fill_space, max_lines_per_segment=4, ), ) progress(0.5, desc="Aligning audio") print("Starting alignment...") # FIX: Add error handling for alignment try: main(alignment_config) print("Alignment completed successfully") except Exception as e: raise gr.Error(f"Alignment failed: {str(e)}") progress(0.95, desc="Saving generated alignments") ass_path = "word_level.ass" word_ctm_path = "word_level.ctm" segment_ctm_path = "segment_level.ctm" if segments: print("Merging chunk alignment results...") merged_ass = "" header_written = False for i, seg in enumerate(segments): chunk_ass_path = f"{tmpdir}/nfa_output/ass/words/{utt_id}_{i:04d}.ass" if os.path.exists(chunk_ass_path): chunk_lines = [] with open(chunk_ass_path, "r", encoding='utf-8') as f: for line in f: if line.startswith("Dialogue:"): parts = line.split(",", 9) if len(parts) >= 10: chunk_lines.append(parts) elif not header_written: merged_ass += line header_written = True if chunk_lines: for j, parts in enumerate(chunk_lines): local_start = parse_ass_time(parts[1]) local_end = parse_ass_time(parts[2]) global_start = local_start + seg['start'] global_end = local_end + seg['start'] if j == 0: global_start = seg['start'] if j == len(chunk_lines) - 1: global_end = seg['end'] if i < len(segments) - 1: next_start = segments[i+1]['start'] if global_end >= next_start: global_end = next_start - 0.05 if global_start >= global_end: global_start = global_end - 0.01 parts[1] = format_ass_time(global_start) parts[2] = format_ass_time(global_end) merged_ass += ",".join(parts) with open(ass_path, "w", encoding="utf-8") as f: f.write(merged_ass) ass_text = merged_ass for ctm_type, out_path in [("words", word_ctm_path), ("segments", segment_ctm_path)]: merged_ctm = "" for i, seg in enumerate(segments): chunk_ctm_path = f"{tmpdir}/nfa_output/ctm/{ctm_type}/{utt_id}_{i:04d}.ctm" if os.path.exists(chunk_ctm_path): lines = [] with open(chunk_ctm_path, "r", encoding='utf-8') as f: for line in f: parts = line.strip().split() if len(parts) >= 5: lines.append(parts) for j, parts in enumerate(lines): parts[0] = str(utt_id) l_start = float(parts[2]) l_dur = float(parts[3]) l_end = l_start + l_dur g_start = l_start + seg['start'] g_end = l_end + seg['start'] if ctm_type == "segments": g_start = seg['start'] g_end = seg['end'] if i < len(segments) - 1: next_start = segments[i+1]['start'] if g_end >= next_start: g_end = next_start - 0.05 else: if j == 0: g_start = seg['start'] if j == len(lines) - 1: g_end = seg['end'] if i < len(segments) - 1: next_start = segments[i+1]['start'] if g_end >= next_start: g_end = next_start - 0.05 if g_start >= g_end: g_start = g_end - 0.01 parts[2] = f"{g_start:.2f}" parts[3] = f"{(g_end - g_start):.2f}" merged_ctm += " ".join(parts) + "\n" with open(out_path, "w", encoding="utf-8") as f: f.write(merged_ctm) else: print("Processing single alignment result...") ass_file_for_video = f"{tmpdir}/nfa_output/ass/words/{utt_id}.ass" if os.path.exists(ass_file_for_video): with open(ass_file_for_video, "r", encoding="utf-8") as f: ass_text = f.read() with open(ass_path, "w", encoding="utf-8") as f: f.write(ass_text) with open(f"{tmpdir}/nfa_output/ctm/words/{utt_id}.ctm", "r", encoding="utf-8") as f: with open(word_ctm_path, "w", encoding="utf-8") as out_f: out_f.write(f.read()) with open(f"{tmpdir}/nfa_output/ctm/segments/{utt_id}.ctm", "r", encoding="utf-8") as f: with open(segment_ctm_path, "w", encoding="utf-8") as out_f: out_f.write(f.read()) else: raise gr.Error("Alignment did not produce any output files.") print("Generating subtitle formats...") segments_for_subs = parse_ass_to_segments(ass_text) srt_seg_path = "segments.srt" with open(srt_seg_path, "w", encoding="utf-8") as f: f.write(generate_srt_segments(segments_for_subs)) srt_word_path = "word_by_word.srt" with open(srt_word_path, "w", encoding="utf-8") as f: f.write(generate_srt_word_by_word(segments_for_subs)) srt_add_path = "additive.srt" with open(srt_add_path, "w", encoding="utf-8") as f: f.write(generate_srt_additive(segments_for_subs)) lrc_path = "segments.lrc" with open(lrc_path, "w", encoding="utf-8") as f: f.write(generate_lrc(segments_for_subs)) elrc_path = "word_level.elrc" with open(elrc_path, "w", encoding="utf-8") as f: f.write(generate_elrc(segments_for_subs)) print("Generating output video...") full_audio_path = os.path.join(tmpdir, "full_audio.wav") soundfile.write(full_audio_path, audio_data, SAMPLE_RATE) ffmpeg_command = ( f'ffmpeg -y -i "{full_audio_path}" ' f'-f lavfi -i color=c=white:s=1280x720:r=50 ' f'-crf 1 -shortest -vcodec libx264 -pix_fmt yuv420p ' f'-vf "ass=\'{ass_path}\'" ' f'"{output_video_filepath}"' ) print(f"Running FFmpeg command: {ffmpeg_command}") result = os.system(ffmpeg_command) if result != 0 or not os.path.exists(output_video_filepath): raise gr.Error("Failed to generate the output video. FFmpeg command failed.") print("Alignment process completed successfully!") return ( output_video_filepath, gr.update(value=output_info, visible=True if output_info else False), output_video_filepath, gr.update(value=ass_path, visible=True), gr.update(value=word_ctm_path, visible=True), gr.update(value=segment_ctm_path, visible=True), gr.update(value=srt_seg_path, visible=True), gr.update(value=srt_word_path, visible=True), gr.update(value=srt_add_path, visible=True), gr.update(value=lrc_path, visible=True), gr.update(value=elrc_path, visible=True) ) def delete_non_tmp_video(video_path): if video_path: if os.path.exists(video_path): os.remove(video_path) return None with gr.Blocks(title="NeMo Forced Aligner", theme="huggingface") as demo: non_tmp_output_video_filepath = gr.State([]) with gr.Row(): with gr.Column(): gr.Markdown("# NeMo Forced Aligner") gr.Markdown( "Demo for [NeMo Forced Aligner](https://github.com/NVIDIA/NeMo/tree/main/tools/nemo_forced_aligner) (NFA). " "Upload audio/video in Tamazight and (optionally) the text spoken to generate highlighted karaoke subtitles. " "**Now supports syncing with pre-timed SRT or LRC files and generates all subtitle formats instantly!**", ) with gr.Row(): with gr.Column(scale=1): gr.Markdown("## Input") mic_in = gr.Audio(sources=["microphone"], type='filepath', label="Microphone input") audio_file_in = gr.Audio(sources=["upload"], type='filepath', label="Audio file upload") video_file_in = gr.Video(label="Video file upload (Audio will be extracted automatically)") subs_file_in = gr.File(label="[Optional] Upload an SRT or LRC file to constrain alignment to predefined timestamps", file_types=[".srt", ".lrc"]) ref_text = gr.Textbox( label="[Optional] The reference text. Use '|' separators to specify which text will appear together. " "Leave this field blank to use an ASR model's transcription as the reference text instead. (Ignored if SRT/LRC is uploaded)" ) split_on_newline = gr.Checkbox( True, label="Separate text on new lines", ) submit_button = gr.Button("Submit") with gr.Column(scale=1): gr.Markdown("## Output Video") video_out = gr.Video(label="Output Video") text_out = gr.Textbox(label="Output Info", visible=False) gr.Markdown("## Download Subtitle Files") with gr.Row(): ass_file = gr.File(label="ASS (Karaoke)", visible=False) word_ctm_file = gr.File(label="CTM (Word-level)", visible=False) segment_ctm_file = gr.File(label="CTM (Segment-level)", visible=False) with gr.Row(): srt_seg_file = gr.File(label="SRT (Segments)", visible=False) srt_word_file = gr.File(label="SRT (Word-by-Word)", visible=False) srt_add_file = gr.File(label="SRT (Additive)", visible=False) with gr.Row(): lrc_file = gr.File(label="LRC (Segments)", visible=False) elrc_file = gr.File(label="ELRC (Word-level)", visible=False) with gr.Row(): gr.HTML( "

" "Tutorial: \"How to use NFA?\" ๐Ÿš€ | " "Blog post: \"How does forced alignment work?\" ๐Ÿ“š | " "NFA Github page ๐Ÿ‘ฉโ€๐Ÿ’ป" "

" ) submit_button.click( fn=align, inputs=[mic_in, audio_file_in, video_file_in, subs_file_in, ref_text, split_on_newline], outputs=[ video_out, text_out, non_tmp_output_video_filepath, ass_file, word_ctm_file, segment_ctm_file, srt_seg_file, srt_word_file, srt_add_file, lrc_file, elrc_file ], ).then( fn=delete_non_tmp_video, inputs=[non_tmp_output_video_filepath], outputs=None, ) example_2 = """โตœโดฐโดฝโตŸโตŸโต“โตŽโตœ โต โตœโต™โดฐโดทโต“โดผโตœ. โต™ โต‰โต™โตŽ โต โต•โดฑโดฑโต‰ โดฐโตŽโดฐโตโตโดฐโตข โดฐโตŽโต™โตŽโต“โตโตโต“. โดฐโตŽโต“โตข โต‰ โต•โดฑโดฑโต‰ โตโตโต‰ โตŽโต“ โตœโดณโดฐ โตœโต“โตโต–โต‰โตœ โตœโต‰โตโตโต™, โต•โดฑโดฑโต‰ โต โต‰โต–โตฅโตกโดฐโต•โต, โดฝโต”โดฐ โดณโดฐโต. โดฐโตŽโดฐโตโตโดฐโตข โดฐโตŽโต™โตŽโต“โตโตโต“, โต– โตœโตŽโตฃโตกโดฐโต”โต“โตœ โต“โตโดฐ โต– โตœโตŽโดณโดณโดฐโต”โต“โตœ. โดฐโดณโตโตโต‰โดท โต โตกโดฐโต™โต™ โต โต“โดผโต”โดฐ, โดฐโต™โต™ โต โต“โต™โต™โตƒโต™โต“, โดฝโต”โดฐโต‰โดณโดฐโตœ โตขโดฐโต โดท โตŽโดฐโดท โต‰โต™โดฝโต”. โต€โดฐ โตโต โดฝโตขโตขโต‰ โดฝโดฐ โต™ โตโต™โต™โต“โตŽโดท, โดท โดฝโตขโตขโต‰ โดฝโดฐ โดฐโดท โตโตŽโตŽโตœโต”. โต™โตŽโต“โต โดฐโต–, โตœโตŽโตโตœ โดฐโต–, โดฐโต–โดฐโต”โดฐโต™ โตขโต“โต–โดทโต. โดฐโต–โดฐโต”โดฐโต™ โต โต–โตกโต‰โตโตโต‰ โตœโต™โตโตโต“โดผโดฐโตœ, โต“โต” โดท โดฐโตขโตœ โตœโต‰โตขโต“โต”โต‰, โต“โตโดฐ โต‰โตŽโต“โดนโดนโดฐโต•.""" examples = gr.Examples( examples=[ ["Voice1410.wav", None, example_2], ["Tamazight_For_All.mp3", "Tamazight_For_All.srt", ""] ], inputs=[audio_file_in, subs_file_in, ref_text] ) demo.queue() demo.launch()