Update app.py
Browse files
app.py
CHANGED
|
@@ -11,11 +11,6 @@ os.system('bash ./whisper.cpp/models/download-ggml-model.sh medium')
|
|
| 11 |
os.system('bash ./whisper.cpp/models/download-ggml-model.sh large')
|
| 12 |
os.system('bash ./whisper.cpp/models/download-ggml-model.sh base.en')
|
| 13 |
|
| 14 |
-
#os.system('./whisper.cpp/main -m whisper.cpp/models/ggml-base.en.bin -f whisper.cpp/samples/jfk.wav')
|
| 15 |
-
#print("SEURAAVAKSI SMALL TESTI")
|
| 16 |
-
#os.system('./whisper.cpp/main -m whisper.cpp/models/ggml-small.bin -f whisper.cpp/samples/jfk.wav')
|
| 17 |
-
#print("MOI")
|
| 18 |
-
|
| 19 |
|
| 20 |
import gradio as gr
|
| 21 |
from pathlib import Path
|
|
@@ -25,11 +20,7 @@ import re
|
|
| 25 |
import time
|
| 26 |
|
| 27 |
from pytube import YouTube
|
| 28 |
-
#from transformers import MarianMTModel, MarianTokenizer
|
| 29 |
|
| 30 |
-
import psutil
|
| 31 |
-
num_cores = psutil.cpu_count()
|
| 32 |
-
os.environ["OMP_NUM_THREADS"] = f"{num_cores}"
|
| 33 |
headers = {'Authorization': os.environ['DeepL_API_KEY']}
|
| 34 |
|
| 35 |
|
|
@@ -227,7 +218,8 @@ def speech_to_text(video_file_path, selected_source_lang, whisper_model):
|
|
| 227 |
2. Watch it in the first video component
|
| 228 |
3. Run automatic speech recognition on the video using fast Whisper models
|
| 229 |
4. Translate the recognized transcriptions to 26 languages supported by deepL
|
| 230 |
-
5.
|
|
|
|
| 231 |
|
| 232 |
Speech Recognition is based on models from OpenAI Whisper https://github.com/openai/whisper
|
| 233 |
This space is using c++ implementation by https://github.com/ggerganov/whisper.cpp
|
|
|
|
| 11 |
os.system('bash ./whisper.cpp/models/download-ggml-model.sh large')
|
| 12 |
os.system('bash ./whisper.cpp/models/download-ggml-model.sh base.en')
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
import gradio as gr
|
| 16 |
from pathlib import Path
|
|
|
|
| 20 |
import time
|
| 21 |
|
| 22 |
from pytube import YouTube
|
|
|
|
| 23 |
|
|
|
|
|
|
|
|
|
|
| 24 |
headers = {'Authorization': os.environ['DeepL_API_KEY']}
|
| 25 |
|
| 26 |
|
|
|
|
| 218 |
2. Watch it in the first video component
|
| 219 |
3. Run automatic speech recognition on the video using fast Whisper models
|
| 220 |
4. Translate the recognized transcriptions to 26 languages supported by deepL
|
| 221 |
+
5. Download generated subtitles in .vtt and .srt formats
|
| 222 |
+
6. Watch the the original video with generated subtitles
|
| 223 |
|
| 224 |
Speech Recognition is based on models from OpenAI Whisper https://github.com/openai/whisper
|
| 225 |
This space is using c++ implementation by https://github.com/ggerganov/whisper.cpp
|