Spaces:
Runtime error
Runtime error
| ''' | |
| This script calls the ada model from openai api to predict the next few words. | |
| ''' | |
| import os | |
| os.system("pip install --upgrade pip") | |
| from pprint import pprint | |
| os.system("pip install git+https://github.com/openai/whisper.git") | |
| import openai | |
| import gradio as gr | |
| import whisper | |
| from transformers import pipeline | |
| import torch | |
| from transformers import AutoModelForCausalLM | |
| from transformers import AutoTokenizer | |
| import time | |
| # import streaming.py | |
| # from next_word_prediction import GPT2 | |
| #gpt2 = AutoModelForCausalLM.from_pretrained("gpt2", return_dict_in_generate=True) | |
| #tokenizer = AutoTokenizer.from_pretrained("gpt2") | |
| ### /code snippet | |
| # get gpt2 model | |
| generator = pipeline('text-generation', model='gpt2') | |
| # whisper model specification | |
| model = whisper.load_model("tiny") | |
| def inference(audio, state=""): | |
| #time.sleep(2) | |
| #text = p(audio)["text"] | |
| #state += text + " " | |
| # load audio data | |
| audio = whisper.load_audio(audio) | |
| # ensure sample is in correct format for inference | |
| audio = whisper.pad_or_trim(audio) | |
| # generate a log-mel spetrogram of the audio data | |
| mel = whisper.log_mel_spectrogram(audio).to(model.device) | |
| _, probs = model.detect_language(mel) | |
| # decode audio data | |
| options = whisper.DecodingOptions(fp16 = False) | |
| # transcribe speech to text | |
| result = whisper.decode(model, mel, options) | |
| print("result pre gp model from whisper: ", result, ".text ", result.text) | |
| PROMPT = """The following is a transcript of a conversation. Predict the next few words in the conversation as a List of options. | |
| A few examples are provided below and then the current transcript is provided. | |
| Examples: | |
| Transcript: Tomorrow night we're going out to | |
| Next: The Movies to watch a blockbuster, A Restaurant for dinner, A Baseball Game, The Theater, A Party for a friend | |
| Transcript: I would like to order a cheeseburger with a side of | |
| Next: Frnech fries, Milkshake, Apple slices, Side salad, Extra katsup | |
| Transcript: My friend Savanah is | |
| Next: An elecrical engineer, A marine biologist, A classical musician | |
| Transcript: I need to buy a birthday | |
| Next: Present, Gift, Cake, Card | |
| """ | |
| text = PROMPT + result.text | |
| openai.api_key = os.environ["Openai_APIkey"] | |
| response = openai.Completion.create( | |
| model="text-ada-001", | |
| #model="text-curie-001", | |
| prompt=text, | |
| temperature=0.3, | |
| max_tokens=8, | |
| n=5) | |
| infers =[] | |
| for i in range(5): | |
| print("print1 ", response['choices'][i]['text']) | |
| infers.append(response['choices'][i]['text']) | |
| print("print2: infers ", infers) | |
| print("print3: Responses ", response) | |
| print("Object type of response: ", type(response)) | |
| # result.text | |
| #return getText, gr.update(visible=True), gr.update(visible=True), gr.update(visible=True) | |
| return result.text, state, infers | |
| # get audio from microphone | |
| gr.Interface( | |
| fn=inference, | |
| inputs=[ | |
| gr.inputs.Audio(source="microphone", type="filepath"), | |
| "state" | |
| ], | |
| outputs=[ | |
| "textbox", | |
| "state", | |
| "textbox" | |
| ], | |
| live=True).launch() | |