ekacare

/

parrotlet-a-en-5b

like 4

Follow

Eka Care 67

I'm passing in the audio of 40 secs but the model transcribes uptill 20 secs. What could be the issue? Am I missing anything?

I even tried setting max_new_tokens=8192, still no luck.

from transformers import AutoModel
import librosa

repo_name = "ekacare/parrotlet-a-en-5b"
model = AutoModel.from_pretrained(repo_name, trust_remote_code=True)

audio_path = "<myaudio.wav>"
audio, sample_rate = librosa.load(audio_path, sr=16000)

transcription = model.transcribe(audio, sample_rate)
print("Transcription:", transcription)

Also on a side note: Do you provide API? The API documentation seems to be in progress, I see 404!