File size: 1,375 Bytes
d1f611f
 
e6bde5b
 
d1f611f
e6bde5b
d1f611f
 
23f8016
d1f611f
 
 
 
 
 
 
 
 
 
 
23f8016
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d1f611f
 
 
 
 
 
 
34819e5
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
# from whisper_jax import FlaxWhisperPipline
# import jax.numpy as jnp
# import whisper
# print(whisper.__file__)
from openai import OpenAI
from decouple import config
import os

OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
client = OpenAI()
os.environ['OPENAI_API_KEY'] = OPENAI_API_KEY


# def whisper_pipeline_tpu(audio):
#     pipeline = FlaxWhisperPipline("openai/whisper-large-v3", dtype=jnp.bfloat16, batch_size=16)
#     text = pipeline(audio)
#     return text


     
# def whisper_pipeline(audio_path):
#     model = whisper.load_model("medium")
#     # load audio and pad/trim it to fit 30 seconds
#     audio = whisper.load_audio(audio_path)
#     audio = whisper.pad_or_trim(audio)
#     # make log-Mel spectrogram and move to the same device as the model
#     mel = whisper.log_mel_spectrogram(audio).to(model.device)
#     # detect the spoken language
#     _, probs = model.detect_language(mel)
#     print(f"Detected language: {max(probs, key=probs.get)}")
#     # decode the audio
#     options = whisper.DecodingOptions()
#     result = whisper.decode(model, mel, options)
#     # print the recognized text
#     print(result.text)
#     return result.text

def whisper_openai(audio_path):
   audio_file= open(audio_path, "rb")
   transcript = client.audio.transcriptions.create(
    model="whisper-1", 
    file=audio_file
   )
   return transcript