Duplicate from bofenghuang/whisper-demo-french

Co-authored-by: bofeng huang <bofenghuang@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,15 @@
+---
+title: Whisper French Demo
+emoji: 🤫
+colorFrom: indigo
+colorTo: red
+sdk: gradio
+sdk_version: 3.9.1
+app_file: app.py
+pinned: false
+tags:
+- whisper-event
+duplicated_from: bofenghuang/whisper-demo-french
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1 @@
+run_demo_multi_models.py

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,3 @@
+git+https://github.com/huggingface/transformers
+torch
+pytube

run_demo.py

@@ -0,0 +1,97 @@
+import torch
+
+import gradio as gr
+import pytube as pt
+from transformers import pipeline
+from huggingface_hub import model_info
+
+MODEL_NAME = "bofenghuang/whisper-medium-cv11-french-punct"
+CHUNK_LENGTH_S = 30
+
+device = 0 if torch.cuda.is_available() else "cpu"
+pipe = pipeline(
+    task="automatic-speech-recognition",
+    model=MODEL_NAME,
+    chunk_length_s=CHUNK_LENGTH_S,
+    device=device,
+)
+
+pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="fr", task="transcribe")
+
+def transcribe(microphone, file_upload):
+    warn_output = ""
+    if (microphone is not None) and (file_upload is not None):
+        warn_output = (
+            "WARNING: You've uploaded an audio file and used the microphone. "
+            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
+        )
+
+    elif (microphone is None) and (file_upload is None):
+        return "ERROR: You have to either use the microphone or upload an audio file"
+
+    file = microphone if microphone is not None else file_upload
+
+    text = pipe(file)["text"]
+
+    return warn_output + 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 yt_transcribe(yt_url):
+    yt = pt.YouTube(yt_url)
+    html_embed_str = _return_yt_html_embed(yt_url)
+    stream = yt.streams.filter(only_audio=True)[0]
+    stream.download(filename="audio.mp3")
+
+    text = pipe("audio.mp3")["text"]
+
+    return html_embed_str, text
+
+
+demo = gr.Blocks()
+
+mf_transcribe = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
+        gr.inputs.Audio(source="upload", type="filepath", optional=True),
+    ],
+    outputs="text",
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Demo: Transcribe Audio",
+    description=(
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the the fine-tuned"
+        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")],
+    outputs=["html", "text"],
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Demo: Transcribe YouTube",
+    description=(
+        "Transcribe long-form YouTube videos with the click of a button! Demo uses the the fine-tuned checkpoint:"
+        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files of"
+        " arbitrary length."
+    ),
+    allow_flagging="never",
+)
+
+with demo:
+    gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
+
+demo.launch(enable_queue=True)

run_demo_multi_models.py

@@ -0,0 +1,148 @@
+import logging
+import warnings
+
+import gradio as gr
+import pytube as pt
+import torch
+from huggingface_hub import model_info
+from transformers import pipeline
+from transformers.utils.logging import disable_progress_bar
+
+warnings.filterwarnings("ignore")
+disable_progress_bar()
+
+DEFAULT_MODEL_NAME = "bofenghuang/whisper-medium-cv11-french-punct"
+MODEL_NAMES = [
+    "openai/whisper-small",
+    "openai/whisper-medium",
+    "openai/whisper-large-v2",
+    "bofenghuang/whisper-small-cv11-french",
+    "bofenghuang/whisper-small-cv11-french-punct",
+    "bofenghuang/whisper-medium-cv11-french",
+    "bofenghuang/whisper-medium-cv11-french-punct",
+]
+CHUNK_LENGTH_S = 30
+MAX_NEW_TOKENS = 225
+
+logging.basicConfig(
+    format="%(asctime)s [%(levelname)s] [%(name)s] %(message)s",
+    datefmt="%Y-%m-%dT%H:%M:%SZ",
+)
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.DEBUG)
+
+device = 0 if torch.cuda.is_available() else "cpu"
+logger.info(f"Model will be loaded on device {device}")
+
+cached_models = {}
+
+def maybe_load_cached_pipeline(model_name):
+    pipe = cached_models.get(model_name)
+    if pipe is None:
+        # load pipeline
+        # todo: set decoding option for pipeline
+        pipe = pipeline(
+            task="automatic-speech-recognition",
+            model=model_name,
+            chunk_length_s=CHUNK_LENGTH_S,
+            device=device,
+        )
+        # set forced_decoder_ids
+        pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="fr", task="transcribe")
+        # limit genneration max length
+        pipe.model.config.max_length = MAX_NEW_TOKENS + 1
+
+        logger.info(f"`{model_name}` pipeline has been initialized")
+
+        cached_models[model_name] = pipe
+    return pipe
+
+
+def transcribe(microphone, file_upload, model_name):
+    warn_output = ""
+    if (microphone is not None) and (file_upload is not None):
+        warn_output = (
+            "WARNING: You've uploaded an audio file and used the microphone. "
+            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
+        )
+
+    elif (microphone is None) and (file_upload is None):
+        return "ERROR: You have to either use the microphone or upload an audio file"
+
+    file = microphone if microphone is not None else file_upload
+
+    pipe = maybe_load_cached_pipeline(model_name)
+    text = pipe(file)["text"]
+
+    logger.info(f"Transcription: {text}")
+
+    return warn_output + 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 yt_transcribe(yt_url, model_name):
+    yt = pt.YouTube(yt_url)
+    html_embed_str = _return_yt_html_embed(yt_url)
+    stream = yt.streams.filter(only_audio=True)[0]
+    stream.download(filename="audio.mp3")
+
+    pipe = maybe_load_cached_pipeline(model_name)
+    text = pipe("audio.mp3")["text"]
+
+    logger.info(f"Transcription: {text}")
+
+    return html_embed_str, text
+
+
+# load default model
+maybe_load_cached_pipeline(DEFAULT_MODEL_NAME)
+
+demo = gr.Blocks()
+
+mf_transcribe = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath", optional=True, label="Record"),
+        gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Upload File"),
+        gr.inputs.Dropdown(choices=MODEL_NAMES, default=DEFAULT_MODEL_NAME, label="Whisper Model"),
+    ],
+    # outputs="text",
+    outputs=gr.outputs.Textbox(label="Transcription"),
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Demo: Transcribe Audio",
+    description="Transcribe long-form microphone or audio inputs with the click of a button!",
+    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.Dropdown(choices=MODEL_NAMES, default=DEFAULT_MODEL_NAME, label="Whisper Model"),
+    ],
+    # outputs=["html", "text"],
+    outputs=[
+        gr.outputs.HTML(label="YouTube Page"),
+        gr.outputs.Textbox(label="Transcription"),
+    ],
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Demo: Transcribe YouTube",
+    description="Transcribe long-form YouTube videos with the click of a button!",
+    allow_flagging="never",
+)
+
+with demo:
+    gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
+
+# demo.launch(server_name="0.0.0.0", debug=True, share=True)
+demo.launch(enable_queue=True)