Spaces:
Running
Running
| import os | |
| import transformers | |
| import torch | |
| from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig | |
| from transformers import AutoModelForSeq2SeqLM, pipeline | |
| from huggingface_hub import login | |
| import gradio as gr | |
| import numpy as np | |
| new_model = "tensorgirl/finetuned-gemma" | |
| model = AutoModelForCausalLM.from_pretrained(new_model, trust_remote_code=True) | |
| tokenizer = AutoTokenizer.from_pretrained(new_model, trust_remote_code=True) | |
| tokenizer.pad_token = tokenizer.eos_token | |
| generator = transformers.pipeline( | |
| "text-generation", | |
| model=model, | |
| tokenizer=tokenizer, | |
| torch_dtype=torch.bfloat16, | |
| trust_remote_code=True, | |
| device_map="auto", | |
| ) | |
| model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M") | |
| tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M") | |
| device = 0 if torch.cuda.is_available() else -1 | |
| def translate(text, src_lang, tgt_lang): | |
| translation_pipeline = pipeline("translation", model=model, tokenizer=tokenizer, src_lang=src_lang, tgt_lang=tgt_lang, max_length=400, device=device) | |
| result = translation_pipeline(text) | |
| return result[0]['translation_text'] | |
| def English(audio): | |
| transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en") | |
| sr, y = audio | |
| y = y.astype(np.float32) | |
| y /= np.max(np.abs(y)) | |
| return transcriber({"sampling_rate": sr, "raw": y})["text"] | |
| def Hindi(audio): | |
| transcriber = pipeline("automatic-speech-recognition", model="theainerd/Wav2Vec2-large-xlsr-hindi") | |
| sr, y = audio | |
| y = y.astype(np.float32) | |
| y /= np.max(np.abs(y)) | |
| text = transcriber({"sampling_rate":sr, "raw":y})["text"] | |
| return translate(text, "hin_Deva", "eng_Latn") | |
| def Telegu(audio): | |
| transcriber = pipeline("automatic-speech-recognition", model="anuragshas/wav2vec2-large-xlsr-53-telugu") | |
| sr, y = audio | |
| y = y.astype(np.float32) | |
| y /= np.max(np.abs(y)) | |
| text = transcriber({"sampling_rate":sr, "raw":y})["text"] | |
| return translate(text, "tel_Telu", "eng_Latn") | |
| def Tamil(audio): | |
| transcriber = pipeline("automatic-speech-recognition", model="Harveenchadha/vakyansh-wav2vec2-tamil-tam-250") | |
| sr, y = audio | |
| y = y.astype(np.float32) | |
| y /= np.max(np.abs(y)) | |
| text = transcriber({"sampling_rate":sr, "raw":y})["text"] | |
| return translate(text, "tam_Taml", "eng_Latn") | |
| def Kannada(audio): | |
| transcriber = pipeline("automatic-speech-recognition", model="vasista22/whisper-kannada-medium") | |
| sr, y = audio | |
| y = y.astype(np.float32) | |
| y /= np.max(np.abs(y)) | |
| text = transcriber({"sampling_rate":sr, "raw":y})["text"] | |
| return translate(text, "kan_Knda", "eng_Latn") | |
| def predict(audio, language): | |
| if language == "English": | |
| message = English(audio) | |
| if language == "Hindi": | |
| message = Hindi(audio) | |
| if language == "Telegu": | |
| message = Telegu(audio) | |
| if language == "Tamil": | |
| message = Tamil(audio) | |
| if language == "Kannada": | |
| message = Kannada(audio) | |
| print(message) | |
| sequences = generator( | |
| message, | |
| max_length=200, | |
| do_sample=False, | |
| top_k=10, | |
| num_return_sequences=1, | |
| eos_token_id=tokenizer.eos_token_id,) | |
| answer = "" | |
| for seq in sequences: | |
| answer = answer + seq['generated_text'] + " " | |
| print(answer) | |
| if language == "English": | |
| return answer | |
| if language == "Hindi": | |
| return translate(answer,"eng_Latn", "hin_Deva") | |
| if language == "Telegu": | |
| return translate(answer,"eng_Latn", "tel_Telu") | |
| if language == "Tamil": | |
| return translate(answer, "eng_Latn", "tam_Taml") | |
| if language == "Kannada": | |
| return translate(answer, "eng_Latn", "kan_Knda") | |
| return answer | |
| demo = gr.Interface( | |
| predict, | |
| [gr.Audio(), | |
| gr.Dropdown( | |
| ["Hindi", "Telegu", "Tamil", "Kannada", "English"], label="Language", info="Please select language of your choice" | |
| )], | |
| "text", | |
| title = "Farmers-Helper-Bot", | |
| description = "Ask your queries in your regional Language" | |
| ) | |
| demo.launch(share=True) |