ValueError: text input must of type `str` (single example), `List[str]` (batch or single pretokenized example) or `List[List[str]]` (batch of pretokenized examples).

[Ushanjay]

import soundfile as sf
from scipy.io import wavfile
from IPython.display import Audio
from transformers import Wav2Vec2ForCTC, Wav2Vec2CTCTokenizer

import speech_recognition as sr
import io
from pydub import AudioSegment

tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("facebook/wav2vec2-base-960h")
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")

r = sr.Recognizer()
with sr.Microphone(sample_rate=16000) as source:
print("speak")
while True:
audio = r.listen(source)
data = io.BytesIO(audio.get_wav_data())
clip = AudioSegment.from_file(data)
x = torch.FloatTensor(clip.get_array_of_samples())
print(x)

    inputs = tokenizer(x, sampling_rate=16000, return_tensors='pt', padding='longest').input_values
    logits = model(inputs).logits
    tokens = torch.argmax(logits, axis=-1)
    text = tokenizer.batch_decode(tokens)

    print('you said: ', str(text).lower())

[Frank Palma Gomez]

take a look at #10