Spaces:
Sleeping
Sleeping
File size: 4,152 Bytes
7f8cb6d 86d71e1 7f8cb6d 6cc56c2 a8c9cb0 21c55ca 7f8cb6d e45c4d4 6d25e94 7f8cb6d 47a0256 6cc56c2 7f8cb6d 6cc56c2 7f8cb6d b98b6d3 6cc56c2 a0e5730 7f8cb6d 6cc56c2 7f8cb6d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 |
import gradio as gr
from transformers import pipeline
from transformers import M2M100Tokenizer, M2M100ForConditionalGeneration
pretrained_model: str = "facebook/m2m100_1.2B"
cache_dir: str = "models/"
tokenizer = M2M100Tokenizer.from_pretrained(pretrained_model, cache_dir=cache_dir)
translation_model = M2M100ForConditionalGeneration.from_pretrained(
pretrained_model, cache_dir=cache_dir)
transcription = pipeline("automatic-speech-recognition", model= "openai/whisper-base")
clasification = pipeline(
"audio-classification",
model="anton-l/xtreme_s_xlsr_300m_minds14",
)
def audio_a_text(audio):
text = transcription(audio)["text"]
return text
def text_to_sentimient(audio):
#text = transcription(audio)["text"]
return clasification(audio)
lang_id = {
"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 translation(source_lang, target_lang):
src_lang = lang_id[source_lang]
trg_lang = lang_id[target_lang]
tokenizer.src_lang = src_lang
with torch.no_grad():
encoded_input = tokenizer(user_input, return_tensors="pt").to(device)
generated_tokens = model.generate(
**encoded_input, forced_bos_token_id=tokenizer.get_lang_id(trg_lang))
translated_text = tokenizer.batch_decode(
generated_tokens, skip_special_tokens=True)[0]
return translated_text
demo = gr.Blocks()
with demo:
gr.Markdown("Speech analyzer")
audio = gr.Audio(type="filepath", label = "Upload a file")
text0 = gr.Textbox()
text = gr.Textbox()
source_lang = gr.Dropdown(label="Source lang", choices=list(lang_id.keys()))
target_lang = gr.Dropdown(label="target lang", choices=list(lang_id.keys()))
#gr.Examples(examples = list(lang_id.keys()),
# inputs=[
# source_lang])
b1 = gr.Button("convert to text")
b3 = gr.Button("translate")
b3.Dropdown(translation, input = text0, output = text)
b1.click(audio_a_text, inputs=audio, outputs=text)
b2 = gr.Button("Classification of speech")
b2.click(text_to_sentimient, inputs=audio, outputs=text)
demo.launch()
|