Create app.py

app.py

@@ -0,0 +1,204 @@
+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 numpy as np
+from huggingface_hub import snapshot_download
+from fairseq2.assets import InProcAssetMetadataProvider, asset_store
+from seamless_communication.inference import Translator
+
+import tempfile
+import os
+
+
+#from lang_list import (
+    #ASR_TARGET_LANGUAGE_NAMES,
+    #LANGUAGE_NAME_TO_CODE,
+    #S2ST_TARGET_LANGUAGE_NAMES,
+    #S2TT_TARGET_LANGUAGE_NAMES,
+    #T2ST_TARGET_LANGUAGE_NAMES,
+    #T2TT_TARGET_LANGUAGE_NAMES,
+    #TEXT_SOURCE_LANGUAGE_NAMES,
+#)
+
+CHECKPOINTS_PATH = pathlib.Path(os.getenv("CHECKPOINTS_PATH", "/home/user/app/models"))
+if not CHECKPOINTS_PATH.exists():
+    snapshot_download(repo_id="facebook/seamless-m4t-v2-large", repo_type="model", local_dir=CHECKPOINTS_PATH)
+asset_store.env_resolvers.clear()
+asset_store.env_resolvers.append(lambda: "demo")
+demo_metadata = [
+    {
+        "name": "seamlessM4T_v2_large@demo",
+        "checkpoint": f"file://{CHECKPOINTS_PATH}/seamlessM4T_v2_large.pt",
+        "char_tokenizer": f"file://{CHECKPOINTS_PATH}/spm_char_lang38_tc.model",
+    },
+    {
+        "name": "vocoder_v2@demo",
+        "checkpoint": f"file://{CHECKPOINTS_PATH}/vocoder_v2.pt",
+    },
+]
+asset_store.metadata_providers.append(InProcAssetMetadataProvider(demo_metadata))
+
+
+MODEL_NAME = "openai/whisper-large-v2"
+BATCH_SIZE = 8
+FILE_LIMIT_MB = 1000
+YT_LENGTH_LIMIT_S = 3600  # limit to 1 hour YouTube files
+
+DEFAULT_TARGET_LANGUAGE = "French"
+
+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 run_s2tt(input_audio: str, source_language: str, target_language: str) -> str:
+    preprocess_audio(input_audio)
+    source_language_code = LANGUAGE_NAME_TO_CODE[source_language]
+    target_language_code = LANGUAGE_NAME_TO_CODE[target_language]
+    out_texts, _ = translator.predict(
+        input=input_audio,
+        task_str="S2TT",
+        src_lang=source_language_code,
+        tgt_lang=target_language_code,
+    )
+    return str(out_texts[0])
+
+
+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"]
+
+    # Traduire le texte transcrit en français
+    translated_text = run_s2tt(text, source_language, target_language) 
+    return translated_text
+
+
+def _return_yt_html_embed(yt_url):
+    video_id = yt_url.split("?v=")[-1]
+    HTML_str = (
+        f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
+        " </center>"
+    )
+    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 yt_transcribe(yt_url, task, max_filesize=75.0):
+    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)
+        with open(filepath, "rb") as f:
+            inputs = f.read()
+
+    inputs = ffmpeg_read(inputs, pipe.feature_extractor.sampling_rate)
+    inputs = {"array": inputs, "sampling_rate": pipe.feature_extractor.sampling_rate}
+
+    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+
+    # Traduire le texte transcrit en français
+    translated_text = run_s2tt(text, source_language, target_language)
+    return html_embed_str, translated_text
+
+
+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)