Playing around xD

README.md

@@ -1,13 +1,11 @@
 ---
 title: WhisperAnything
-emoji: 🦀
-colorFrom: pink
-colorTo: pink
+emoji: 🎙
+colorFrom: red
+colorTo: yellow
 sdk: gradio
 sdk_version: 3.18.0
 app_file: app.py
 pinned: false
 license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---

app.py

@@ -0,0 +1,63 @@
+from multilingual_translation import text_to_text_generation
+from utils import lang_ids, data_scraping
+import whisper
+import gradio as gr
+
+lang_list = list(lang_ids.keys())
+model_list = data_scraping()
+model = whisper.load_model("small")
+
+def transcribe(audio):
+    
+    #time.sleep(3)
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+
+    # make log-Mel spectrogram and move to the same device as the model
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+
+    # detect the spoken language
+    _, probs = model.detect_language(mel)
+    print(f"Detected language: {max(probs, key=probs.get)}")
+
+    # decode the audio
+    options = whisper.DecodingOptions(fp16 = False)
+    result = whisper.decode(model, mel, options)
+
+    finalResult = text_to_text_generation(prompt='return.text', model_id='facebook/m2m100_418M', device='cpu',target_lang='English')
+    return finalResult
+
+# api endpoint to return the transcription in EN as a json response
+
+# @app.route('/transcribe', methods=['POST'])
+# def transcribe_api():
+#     if request.method == 'POST':
+#         audio = request.files['audio']
+#         audio = audio.read()
+#         audio = io.BytesIO(audio)
+#         audio = whisper.load_audio(audio)
+#         audio = whisper.pad_or_trim(audio)
+#         mel = whisper.log_mel_spectrogram(audio).to(model.device)
+#         _, probs = model.detect_language(mel)
+#         print(f"Detected language: {max(probs, key=probs.get)}")
+#         options = whisper.DecodingOptions(fp16 = False)
+#         result = whisper.decode(model, mel, options)
+#         return jsonify(result)
+
+
+    
+    
+ 
+gr.Interface(
+    title = 'OpenAI Whisper ASR Gradio Web UI', 
+    fn=transcribe, 
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath")
+    ],
+    outputs=[
+        "textbox"
+    ],
+    live=True).launch(debug=True, enable_queue=True)
+
+# output = gr.outputs.Textbox(label="Output Text")

requirements.txt

@@ -0,0 +1,6 @@
+torch
+beautifulsoup4==4.11.2
+multilingual_translation==0.0.5
+requests==2.28.1
+tensorflow
+git+https://github.com/openai/whisper.git

utils.py

@@ -0,0 +1,128 @@
+from bs4 import BeautifulSoup
+import requests
+
+
+lang_ids = {
+    "Afrikaans": "af",
+    "Amharic": "am",
+    "Arabic": "ar",
+    "Asturian": "ast",
+    "Azerbaijani": "az",
+    "Bashkir": "ba",
+    "Belarusian": "be",
+    "Bulgarian": "bg",
+    "Bengali": "bn",
+    "Breton": "br",
+    "Bosnian": "bs",
+    "Catalan": "ca",
+    "Cebuano": "ceb",
+    "Czech": "cs",
+    "Welsh": "cy",
+    "Danish": "da",
+    "German": "de",
+    "Greeek": "el",
+    "English": "en",
+    "Spanish": "es",
+    "Estonian": "et",
+    "Persian": "fa",
+    "Fulah": "ff",
+    "Finnish": "fi",
+    "French": "fr",
+    "Western Frisian": "fy",
+    "Irish": "ga",
+    "Gaelic": "gd",
+    "Galician": "gl",
+    "Gujarati": "gu",
+    "Hausa": "ha",
+    "Hebrew": "he",
+    "Hindi": "hi",
+    "Croatian": "hr",
+    "Haitian": "ht",
+    "Hungarian": "hu",
+    "Armenian": "hy",
+    "Indonesian": "id",
+    "Igbo": "ig",
+    "Iloko": "ilo",
+    "Icelandic": "is",
+    "Italian": "it",
+    "Japanese": "ja",
+    "Javanese": "jv",
+    "Georgian": "ka",
+    "Kazakh": "kk",
+    "Central Khmer": "km",
+    "Kannada": "kn",
+    "Korean": "ko",
+    "Luxembourgish": "lb",
+    "Ganda": "lg",
+    "Lingala": "ln",
+    "Lao": "lo",
+    "Lithuanian": "lt",
+    "Latvian": "lv",
+    "Malagasy": "mg",
+    "Macedonian": "mk",
+    "Malayalam": "ml",
+    "Mongolian": "mn",
+    "Marathi": "mr",
+    "Malay": "ms",
+    "Burmese": "my",
+    "Nepali": "ne",
+    "Dutch": "nl",
+    "Norwegian": "no",
+    "Northern Sotho": "ns",
+    "Occitan": "oc",
+    "Oriya": "or",
+    "Panjabi": "pa",
+    "Polish": "pl",
+    "Pushto": "ps",
+    "Portuguese": "pt",
+    "Romanian": "ro",
+    "Russian": "ru",
+    "Sindhi": "sd",
+    "Sinhala": "si",
+    "Slovak": "sk",
+    "Slovenian": "sl",
+    "Somali": "so",
+    "Albanian": "sq",
+    "Serbian": "sr",
+    "Swati": "ss",
+    "Sundanese": "su",
+    "Swedish": "sv",
+    "Swahili": "sw",
+    "Tamil": "ta",
+    "Thai": "th",
+    "Tagalog": "tl",
+    "Tswana": "tn",
+    "Turkish": "tr",
+    "Ukrainian": "uk",
+    "Urdu": "ur",
+    "Uzbek": "uz",
+    "Vietnamese": "vi",
+    "Wolof": "wo",
+    "Xhosa": "xh",
+    "Yiddish": "yi",
+    "Yoruba": "yo",
+    "Chinese": "zh",
+    "Zulu": "zu",
+}
+
+def model_url_list():
+    url_list = []
+    for i in range(0, 5):
+        url_list.append(f"https://huggingface.co/models?other=m2m_100&p={i}&sort=downloads")
+    return url_list
+
+def data_scraping():
+    url_list = model_url_list()
+    model_list = []
+    for url in url_list:
+        response = requests.get(url)
+        soup = BeautifulSoup(response.text, "html.parser")
+        div_class = 'grid grid-cols-1 gap-5 2xl:grid-cols-2'
+        div = soup.find('div', {'class': div_class})
+        for a in div.find_all('a', href=True):
+            model_list.append(a['href'])
+    
+    for i in range(len(model_list)):
+        model_list[i] = model_list[i][1:]
+
+    return model_list