Duplicate from ayaanzaveri/faster-whisper-api

Co-authored-by: Ayaan Zaveri <ayaanzaveri@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 +1,13 @@
+---
+title: Faster Whisper Api
+emoji: ⚡
+colorFrom: blue
+colorTo: blue
+sdk: gradio
+sdk_version: 3.23.0
+app_file: app.py
+pinned: false
+duplicated_from: ayaanzaveri/faster-whisper-api
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,71 @@
+import pathlib
+from faster_whisper import WhisperModel
+import yt_dlp
+import uuid
+import os
+import gradio as gr
+from tqdm import tqdm
+
+# List of all supported video sites here https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md
+def download_convert_video_to_audio(
+    yt_dlp,
+    video_url: str,
+    destination_path: pathlib.Path,
+) -> None:
+    ydl_opts = {
+        "format": "bestaudio/best",
+        "postprocessors": [
+            {  # Extract audio using ffmpeg
+                "key": "FFmpegExtractAudio",
+                "preferredcodec": "mp3",
+            }
+        ],
+        "outtmpl": f"{destination_path}.%(ext)s",
+    }
+    try:
+        print(f"Downloading video from {video_url}")
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            ydl.download(video_url)
+        print(f"Downloaded video from {video_url} to {destination_path}")
+    except Exception as e:
+        raise (e)
+
+def segment_to_dict(segment):
+    segment = segment._asdict()
+    if segment["words"] is not None:
+        segment["words"] = [word._asdict() for word in segment["words"]]
+    return segment
+
+def download_video(video_url: str):
+    download_convert_video_to_audio(yt_dlp, video_url, f"{uuid.uuid4().hex}")
+
+def transcribe_video(video_url: str, word_timestamps: bool = True, model_size: str = "tiny"):
+    print(word_timestamps)
+    print("loading model")
+    model = WhisperModel(model_size, device="cpu", compute_type="int8")
+    # model = WhisperModel(model_size, device="cuda", compute_type="float16")
+    print("getting hex")
+    rand_id = uuid.uuid4().hex
+    print("doing download")
+    download_convert_video_to_audio(yt_dlp, video_url, f"{rand_id}")
+    segments, info = model.transcribe(f"{rand_id}.mp3", beam_size=5, word_timestamps=word_timestamps)
+    segments = [segment_to_dict(segment) for segment in segments]
+    total_duration = round(info.duration, 2)  # Same precision as the Whisper timestamps.
+    print(info)
+    os.remove(f"{rand_id}.mp3")
+    print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
+    print(segments)
+    return segments
+
+# print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
+
+# for segment in segments:
+#     print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
+
+demo = gr.Interface(fn=transcribe_video, inputs=[
+    gr.Textbox(label="Video URL"),
+    gr.Checkbox(label="Word Timestamps", info="Do you want word timestamps in the response?"),
+    gr.Dropdown(label="Model", value="tiny", choices=["tiny", "base", "small"])
+  ], outputs="text")
+
+demo.launch()

requirements.txt

@@ -0,0 +1,10 @@
+fastapi==0.74.*
+requests==2.27.*
+sentencepiece==0.1.*
+torch==1.11.*
+transformers==4.*
+uvicorn[standard]==0.17.*
+faster-whisper==0.3.0
+yt-dlp==2023.3.4
+ffmpeg-python==0.2.0
+gradio