whisper-small-ipa-capt

import torch
from transformers import WhisperProcessor, WhisperForConditionalGeneration
import librosa

# Load model and processor
model_id = "canpolatbulbul/whisper-small-ipa"
processor = WhisperProcessor.from_pretrained(model_id)
model = WhisperForConditionalGeneration.from_pretrained(model_id)

# CRITICAL: Disable forced English output
model.config.forced_decoder_ids = None
model.config.suppress_tokens = []
if model.generation_config is not None:
    model.generation_config.forced_decoder_ids = None
    model.generation_config.suppress_tokens = []

# Load audio
audio, sr = librosa.load("path/to/audio.wav", sr=16000)

# Process audio
input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features

# Generate IPA transcription
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)
input_features = input_features.to(device)

# Use only start-of-transcript token (no language forcing)
decoder_input_ids = torch.tensor([[50258]]).to(device)

with torch.no_grad():
    predicted_ids = model.generate(
        input_features,
        decoder_input_ids=decoder_input_ids,
        forced_decoder_ids=None,
        suppress_tokens=[]
    )

# Decode to IPA
ipa_transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
print(ipa_transcription)

Please call Stella.  
Ask her to bring these things with her from the store:  
Six spoons of fresh snow peas, five thick slabs of blue cheese, 
and maybe a snack for her brother Bob.  We also need a small 
plastic snake and a big toy frog for the kids.  She can scoop 
these things into three red bags, and we will go meet her 
Wednesday at the train station.