File size: 2,598 Bytes
1e090f2
ad81fab
2dd5f48
da685d1
 
 
 
 
 
 
 
 
 
 
91edc36
da685d1
 
91edc36
be5f920
 
 
 
 
da685d1
cf1be34
da685d1
 
 
b8c5e67
be5f920
 
 
 
a50abbe
da685d1
180aa71
 
91edc36
180aa71
 
 
da685d1
 
 
 
 
 
 
f43e8e6
be5f920
70e51f5
adc53e2
da685d1
 
 
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
import gradio as gr   
import librosa 
from transformers import AutoFeatureExtractor, AutoModelForSeq2SeqLM, AutoTokenizer, pipeline


def load_and_fix_data(input_file, model_sampling_rate):
    speech, sample_rate = librosa.load(input_file)
    if len(speech.shape) > 1:
        speech = speech[:, 0] + speech[:, 1]
    if sample_rate != model_sampling_rate:
        speech = librosa.resample(speech, sample_rate, model_sampling_rate)
    return speech


feature_extractor = AutoFeatureExtractor.from_pretrained("jonatasgrosman/wav2vec2-xls-r-1b-spanish")
sampling_rate = feature_extractor.sampling_rate

asr = pipeline("automatic-speech-recognition", model="jonatasgrosman/wav2vec2-xls-r-1b-spanish")



model = AutoModelForSeq2SeqLM.from_pretrained('hackathon-pln-es/t5-small-spanish-nahuatl')
tokenizer = AutoTokenizer.from_pretrained('hackathon-pln-es/t5-small-spanish-nahuatl')

new_line = '\n'

def predict_and_ctc_lm_decode(input_file):
    speech = load_and_fix_data(input_file, sampling_rate)
    transcribed_text = asr(speech, chunk_length_s=10, stride_length_s=1)
    transcribed_text = transcribed_text["text"]
    input_ids = tokenizer('translate Spanish to Nahuatl: ' + transcribed_text, return_tensors='pt').input_ids
    outputs = model.generate(input_ids, max_length=512)
    outputs = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
    return f"Spanish Audio Transcription: {transcribed_text} {new_line} Nahuatl Translation :{outputs}"

description = """ This is a Gradio demo of Spanish Audio Transcriptions to Nahuatl Translation. To use this, simply provide an audio input (audio recording or via microphone), which will subsequently be transcribed and translated to the Nahuatl language.

Pre-trained model used for Spanish ASR: [jonatasgrosman/wav2vec2-xls-r-1b-spanish](https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-spanish)

Pre-trained model used for translating Spanish audio transcription to the Nahuatl language: [hackathon-pln-es/t5-small-spanish-nahuatl](https://huggingface.co/hackathon-pln-es/t5-small-spanish-nahuatl)
"""

gr.Interface(
    predict_and_ctc_lm_decode,
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath", label="Record your audio")
    ],
    outputs=[gr.outputs.Textbox()],
    examples=[["audio1.wav"], ["travel.wav"], ["sample_audio.wav"]],
    title="Spanish-Audio-Transcriptions-to-Nahuatl-Translation",
    description = description,
    #article="<p><center><img src='........e'></center></p>",
    layout="horizontal",
    theme="huggingface",
).launch(enable_queue=True, cache_examples=True)