Spaces:
Runtime error
Runtime error
File size: 2,118 Bytes
1726dba 065ecac 1726dba eaaa4aa d130ccc 5cc4f06 147a6a8 5cc4f06 8222fa8 147a6a8 5cc4f06 147a6a8 8de914b 8222fa8 8de914b 5cc4f06 147a6a8 5cc4f06 147a6a8 5cc4f06 |
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 |
import streamlit as st
from st_audiorec import st_audiorec
import librosa
import soundfile
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
import torch
pipe = None
audio_sample: bytes = None
audio_transcription: str = None
def main ():
print("Run init model")
pipe = init_model()
# x = st.slider('Select a value')
# st.write(x, 'squared is', x * x)
print("Render UI")
wav_audio_data = st_audiorec()
if wav_audio_data is not None:
st.audio(wav_audio_data, format='audio/wav')
print("Load data: audio1")
# dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
# sample = dataset[0]["audio"]
audio_file_path = "data/audio1.wav"
audio_data, sample_rate = librosa.load(audio_file_path)
sample = transcribe(audio_data, pipe)
st.write('Sample:', transcribe(sample))
def init_model ():
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
max_new_tokens=128,
chunk_length_s=30,
batch_size=16,
return_timestamps=True,
torch_dtype=torch_dtype,
device=device,
)
print(f'Init model successful: {model}' )
return pipe
def transcribe (audio_sample: bytes, pipe) -> str:
# dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
# sample = dataset[0]["audio"]
result = pipe(audio_sample)
print(result)
st.write('Result', result["text"])
return result["text"]
if __name__ == "__main__":
main() |