Update app.py

app.py

@@ -1,182 +1,150 @@
-/* eslint-disable camelcase */
-import { pipeline, env } from "@xenova/transformers";
-
-// Disable local models
-env.allowLocalModels = false;
-
-// Define model factories
-// Ensures only one model is created of each type
-class PipelineFactory {
-    static task = null;
-    static model = null;
-    static quantized = null;
-    static instance = null;
-
-    constructor(tokenizer, model, quantized) {
-        this.tokenizer = tokenizer;
-        this.model = model;
-        this.quantized = quantized;
-    }
-
-    static async getInstance(progress_callback = null) {
-        if (this.instance === null) {
-            this.instance = pipeline(this.task, this.model, {
-                quantized: this.quantized,
-                progress_callback,
-
-                // For medium models, we need to load the `no_attentions` revision to avoid running out of memory
-                revision: this.model.includes("/whisper-medium") ? "no_attentions" : "main"
-            });
-        }
-
-        return this.instance;
-    }
-}
-
-self.addEventListener("message", async (event) => {
-    const message = event.data;
-
-    // Do some work...
-    // TODO use message data
-    let transcript = await transcribe(
-        message.audio,
-        message.model,
-        message.multilingual,
-        message.quantized,
-        message.subtask,
-        message.language,
-    );
-    if (transcript === null) return;
-
-    // Send the result back to the main thread
-    self.postMessage({
-        status: "complete",
-        task: "automatic-speech-recognition",
-        data: transcript,
-    });
-});
-
-class AutomaticSpeechRecognitionPipelineFactory extends PipelineFactory {
-    static task = "automatic-speech-recognition";
-    static model = null;
-    static quantized = null;
-}
-
-const transcribe = async (
-    audio,
-    model,
-    multilingual,
-    quantized,
-    subtask,
-    language,
-) => {
-
-    const isDistilWhisper = model.startsWith("distil-whisper/");
-
-    let modelName = model;
-    if (!isDistilWhisper && !multilingual) {
-        modelName += ".en"
-    }
-
-    const p = AutomaticSpeechRecognitionPipelineFactory;
-    if (p.model !== modelName || p.quantized !== quantized) {
-        // Invalidate model if different
-        p.model = modelName;
-        p.quantized = quantized;
-
-        if (p.instance !== null) {
-            (await p.getInstance()).dispose();
-            p.instance = null;
-        }
-    }
-
-    // Load transcriber model
-    let transcriber = await p.getInstance((data) => {
-        self.postMessage(data);
-    });
-
-    const time_precision =
-        transcriber.processor.feature_extractor.config.chunk_length /
-        transcriber.model.config.max_source_positions;
-
-    // Storage for chunks to be processed. Initialise with an empty chunk.
-    let chunks_to_process = [
-        {
-            tokens: [],
-            finalised: false,
-        },
-    ];
-
-    // TODO: Storage for fully-processed and merged chunks
-    // let decoded_chunks = [];
-
-    function chunk_callback(chunk) {
-        let last = chunks_to_process[chunks_to_process.length - 1];
-
-        // Overwrite last chunk with new info
-        Object.assign(last, chunk);
-        last.finalised = true;
-
-        // Create an empty chunk after, if it not the last chunk
-        if (!chunk.is_last) {
-            chunks_to_process.push({
-                tokens: [],
-                finalised: false,
-            });
-        }
-    }
-
-    // Inject custom callback function to handle merging of chunks
-    function callback_function(item) {
-        let last = chunks_to_process[chunks_to_process.length - 1];
-
-        // Update tokens of last chunk
-        last.tokens = [...item[0].output_token_ids];
-
-        // Merge text chunks
-        // TODO optimise so we don't have to decode all chunks every time
-        let data = transcriber.tokenizer._decode_asr(chunks_to_process, {
-            time_precision: time_precision,
-            return_timestamps: true,
-            force_full_sequences: false,
-        });
-
-        self.postMessage({
-            status: "update",
-            task: "automatic-speech-recognition",
-            data: data,
-        });
-    }
-
-    // Actually run transcription
-    let output = await transcriber(audio, {
-        // Greedy
-        top_k: 0,
-        do_sample: false,
-
-        // Sliding window
-        chunk_length_s: isDistilWhisper ? 20 : 30,
-        stride_length_s: isDistilWhisper ? 3 : 5,
-
-        // Language and task
-        language: language,
-        task: subtask,
-
-        // Return timestamps
-        return_timestamps: true,
-        force_full_sequences: false,
-
-        // Callback functions
-        callback_function: callback_function, // after each generation step
-        chunk_callback: chunk_callback, // after each chunk is processed
-    }).catch((error) => {
-        self.postMessage({
-            status: "error",
-            task: "automatic-speech-recognition",
-            data: error,
-        });
-        return null;
-    });
-
-    return output;
-};
+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 = "chiyo123/whisper-small-tonga"
+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'<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"]
+
+    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.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
+    ],
+    outputs="text",
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Large V3: 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 V3: 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 V3: 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)