File size: 1,357 Bytes
b0f1b91 26f728c 94c1047 26f728c b0f1b91 6e87384 6cb326f b0f1b91 |
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 |
from deepspeech import Model
import gradio as gr
import numpy as np
import urllib.request
model_file_path = "deepspeech-0.9.3-models.pbmm"
lm_file_path = "deepspeech-0.9.3-models.scorer"
url = "https://github.com/mozilla/DeepSpeech/releases/download/v0.9.3/"
urllib.request.urlretrieve(url + model_file_path, filename=model_file_path)
urllib.request.urlretrieve(url + lm_file_path, filename=lm_file_path)
beam_width = 100
lm_alpha = 0.93
lm_beta = 1.18
model = Model(model_file_path)
model.enableExternalScorer(lm_file_path)
model.setScorerAlphaBeta(lm_alpha, lm_beta)
model.setBeamWidth(beam_width)
def reformat_freq(sr, y):
if sr not in (
48000,
16000,
): # Deepspeech only supports 16k, (we convert 48k -> 16k)
raise ValueError("Unsupported rate", sr)
if sr == 48000:
y = (
((y / max(np.max(y), 1)) * 32767)
.reshape((-1, 3))
.mean(axis=1)
.astype("int16")
)
sr = 16000
return sr, y
def transcribe(audio_file):
text = model.stt(audio_file)
return text
demo = gr.Interface(
transcribe,
# [gr.Audio(source="microphone", streaming=True), "state"],
gr.Audio(label="Upload Audio File", source="upload", type="filepath"),
outputs=gr.Textbox(label="Transcript")
)
if __name__ == "__main__":
demo.launch() |