Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| import torch | |
| from transformers import pipeline | |
| from ctransformers import AutoModelForCausalLM, AutoTokenizer | |
| MODEL_NAME = "openai/whisper-tiny" | |
| BATCH_SIZE = 8 | |
| device = 0 if torch.cuda.is_available() else "cpu" | |
| pipe = pipeline( | |
| task="automatic-speech-recognition", | |
| model=MODEL_NAME, | |
| chunk_length_s=30, | |
| device=device, | |
| ) | |
| # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. | |
| llm = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-v0.1-GGUF", model_file="mistral-7b-v0.1.Q4_K_M.gguf", model_type="mistral", gpu_layers=0, hf=True) | |
| tokenizer = AutoTokenizer.from_pretrained(llm) | |
| llm_pipe = pipeline("text-generation", model=llm, tokenizer=tokenizer) | |
| def transcribe(inputs, task = "transcribe"): | |
| if inputs is None: | |
| raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.") | |
| text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"] | |
| return llm_pipe(text, max_new_tokens=256) | |
| iface = gr.Interface( | |
| fn=transcribe, | |
| inputs=[ | |
| gr.Audio(sources="microphone", type="filepath"), | |
| ], | |
| outputs="text", | |
| title="test", | |
| description=( | |
| "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper" | |
| f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files" | |
| " of arbitrary length." | |
| ), | |
| allow_flagging="never", | |
| ) | |
| iface.launch() |