Spaces:
Sleeping
Sleeping
File size: 2,455 Bytes
8ec473b 8954b8d 8ec473b 18f094b 8ec473b |
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 |
import gradio as gr
import torch
import time
import librosa
import soundfile
import nemo.collections.asr as nemo_asr
import tempfile
import os
import uuid
from transformers import BlenderbotTokenizer, BlenderbotForConditionalGeneration
import torch
mname = "facebook/blenderbot-400M-distill"
model = BlenderbotForConditionalGeneration.from_pretrained(mname)
tokenizer = BlenderbotTokenizer.from_pretrained(mname)
def take_last_tokens(inputs, note_history, history):
filterTokenCount = 128 # filter last 128 tokens
if inputs['input_ids'].shape[1] > filterTokenCount:
inputs['input_ids'] = torch.tensor([inputs['input_ids'][0][-filterTokenCount:].tolist()])
inputs['attention_mask'] = torch.tensor([inputs['attention_mask'][0][-filterTokenCount:].tolist()])
note_history = ['</s> <s>'.join(note_history[0].split('</s> <s>')[2:])]
history = history[1:]
return inputs, note_history, history
def add_note_to_history(note, note_history):
note_history.append(note)
note_history = '</s> <s>'.join(note_history)
return [note_history]
SAMPLE_RATE = 16000
model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_en_conformer_transducer_xlarge")
model.change_decoding_strategy(None)
model.eval()
def process_audio_file(file):
data, sr = librosa.load(file)
if sr != SAMPLE_RATE:
data = librosa.resample(data, orig_sr=sr, target_sr=SAMPLE_RATE)
data = librosa.to_mono(data)
return data
def transcribe(audio, state = ""):
if state is None:
state = ""
audio_data = process_audio_file(audio)
with tempfile.TemporaryDirectory() as tmpdir:
audio_path = os.path.join(tmpdir, f'audio_{uuid.uuid4()}.wav')
soundfile.write(audio_path, audio_data, SAMPLE_RATE)
transcriptions = model.transcribe([audio_path])
if type(transcriptions) == tuple and len(transcriptions) == 2:
transcriptions = transcriptions[0]
transcriptions = transcriptions[0]
state = state + transcriptions
return state, state
gr.Interface(
fn=transcribe,
inputs=[
gr.Audio(source="microphone", type='filepath', streaming=True),
"state",
],
outputs=[
"textbox",
"state"
],
layout="horizontal",
theme="huggingface",
title="ASR",
description=f"Automatic Speech Recognition (ASR)",
allow_flagging='never',
live=True
).launch(debug=True)
|