File size: 5,041 Bytes
80f8097 1723f0f 80f8097 9b5a735 80f8097 1723f0f 80f8097 1723f0f 80f8097 1723f0f 80f8097 1723f0f 9b5a735 1723f0f 80f8097 1723f0f ca89278 1723f0f 80f8097 1723f0f 80f8097 1723f0f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
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
import torch
import requests
MODEL_NAME = "ylacombe/whisper-large-v3-turbo"
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):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36'
}
info_loader = youtube_dl.YoutubeDL({'headers': headers})
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})["text"]
return html_embed_str, text
demo = gr.Blocks()
mf_transcribe = gr.Interface(
fn=transcribe,
inputs=[
gr.Audio(type="filepath"),
gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
],
outputs="text",
title="Whisper Large V3 Turbo: 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.Audio(label="Audio file"),
gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
],
outputs="text",
title="Whisper Large V3: Transcribe Audio",
description=(
"Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the checkpoint"
f" [{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.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
],
outputs=["html", "text"],
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.queue().launch() |