import json
import librosa
import torch
from transformers import AutoFeatureExtractor, AutoModel

repo_id = "istomin9192/mHuBERT-147-ipa-ctc-ft"

feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)
model.eval()

with open("ipa_map.json", "r", encoding="utf-8") as f:
    id2phone = {int(k): v for k, v in json.load(f)["id2phone"].items()}

wav, sr = librosa.load(wav_file, sr=16000, mono=True)
inputs = feature_extractor(wav, sampling_rate=16000, return_tensors="pt")

with torch.no_grad():
    logits = model(**inputs).logits[0]

pred_ids = logits.argmax(dim=-1).tolist()
blank_id = model.config.architecture["blank_id"]
phones = []
prev = blank_id
for pid in pred_ids:
    if pid != blank_id and pid != prev:
        phones.append(id2phone[pid])
    prev = pid

print(phones)