import torch import gradio as gr import yt_dlp as youtube_dl from transformers import pipeline from transformers.pipelines.audio_utils import ffmpeg_read import tempfile import os MODEL_NAME = "openai/whisper-large-v2" BATCH_SIZE = 8 FILE_LIMIT_MB = 1000 YT_LENGTH_LIMIT_S = 3600 # limit to 1 hour YouTube files device = 0 if torch.cuda.is_available() else "cpu" pipe = pipeline( task="automatic-speech-recognition", model=MODEL_NAME, chunk_length_s=30, device=device, ) def transcribe(inputs, task): if inputs is None: raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.") text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"] return text def _return_yt_html_embed(yt_url): video_id = yt_url.split("?v=")[-1] HTML_str = ( f'
' "
" ) return HTML_str def download_yt_audio(yt_url, filename): info_loader = youtube_dl.YoutubeDL() try: info = info_loader.extract_info(yt_url, download=False) except youtube_dl.utils.DownloadError as err: raise gr.Error(str(err)) file_length = info["duration_string"] file_h_m_s = file_length.split(":") file_h_m_s = [int(sub_length) for sub_length in file_h_m_s] if len(file_h_m_s) == 1: file_h_m_s.insert(0, 0) if len(file_h_m_s) == 2: file_h_m_s.insert(0, 0) file_length_s = file_h_m_s[0] * 3600 + file_h_m_s[1] * 60 + file_h_m_s[2] if file_length_s > YT_LENGTH_LIMIT_S: yt_length_limit_hms = time.strftime("%HH:%MM:%SS", time.gmtime(YT_LENGTH_LIMIT_S)) file_length_hms = time.strftime("%HH:%MM:%SS", time.gmtime(file_length_s)) raise gr.Error(f"Maximum YouTube length is {yt_length_limit_hms}, got {file_length_hms} YouTube video.") ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"} with youtube_dl.YoutubeDL(ydl_opts) as ydl: try: ydl.download([yt_url]) except youtube_dl.utils.ExtractorError as err: raise gr.Error(str(err)) def ffmpeg_read(file_path, sampling_rate): # This function should use FFmpeg to extract audio and convert it to the desired format and sampling rate. # The exact implementation will depend on your requirements and setup. # For now, I'll provide a placeholder. raise NotImplementedError("Please implement the ffmpeg_read function.") def yt_transcribe(yt_url, task, max_filesize=75.0, segment_length=30*1000): html_embed_str = _return_yt_html_embed(yt_url) with tempfile.TemporaryDirectory() as tmpdirname: filepath = os.path.join(tmpdirname, "video.mp4") download_yt_audio(yt_url, filepath) # Load the audio using pydub audio = AudioSegment.from_file(filepath, format="mp4") # Split the audio into segments segments = [audio[i:i+segment_length] for i in range(0, len(audio), segment_length)] # Transcribe each segment and combine the results transcriptions = [] for segment in segments: with tempfile.NamedTemporaryFile(delete=True, suffix=".wav") as segment_file: segment.export(segment_file.name, format="wav") # Convert the segment using ffmpeg segment_data = ffmpeg_read(segment_file.name, pipe.feature_extractor.sampling_rate) inputs = {"array": segment_data, "sampling_rate": pipe.feature_extractor.sampling_rate} transcription = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"] transcriptions.append(transcription) full_transcription = " ".join(transcriptions) return html_embed_str, full_transcription demo = gr.Blocks() mf_transcribe = gr.Interface( fn=transcribe, inputs=[ gr.inputs.Audio(source="microphone", type="filepath", optional=True), gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"), ], outputs="text", layout="horizontal", theme="huggingface", title="Whisper Large V2: Transcribe Audio", description=( "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the" f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files" " of arbitrary length." ), allow_flagging="never", ) file_transcribe = gr.Interface( fn=transcribe, inputs=[ gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Audio file"), gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"), ], outputs="text", layout="horizontal", theme="huggingface", title="Whisper Large V2: Transcribe Audio", description=( "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the" f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files" " of arbitrary length." ), allow_flagging="never", ) yt_transcribe = gr.Interface( fn=yt_transcribe, inputs=[ gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"), gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe") ], outputs=["html", "text"], layout="horizontal", theme="huggingface", title="Whisper Large V2: Transcribe YouTube", description=( "Transcribe long-form YouTube videos with the click of a button! Demo uses the checkpoint" f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of" " arbitrary length." ), allow_flagging="never", ) with demo: gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"]) demo.launch(enable_queue=True)