Transciption not working - cli

[natan2525]

whisper --model medium --language pl sample.wav

Error code:
/home/natan/.local/lib/python3.10/site-packages/whisper/timing.py:58: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details. def backtrace(trace: np.ndarray): /home/natan/.local/lib/python3.10/site-packages/whisper/transcribe.py:114: UserWarning: FP16 is not supported on CPU; using FP32 instead warnings.warn("FP16 is not supported on CPU; using FP32 instead") Traceback (most recent call last): File "/home/natan/.local/bin/whisper", line 8, in <module> sys.exit(cli()) File "/home/natan/.local/lib/python3.10/site-packages/whisper/transcribe.py", line 437, in cli result = transcribe(model, audio_path, temperature=temperature, **args) File "/home/natan/.local/lib/python3.10/site-packages/whisper/transcribe.py", line 142, in transcribe tokenizer = get_tokenizer(model.is_multilingual, language=language, task=task) File "/home/natan/.local/lib/python3.10/site-packages/whisper/tokenizer.py", line 385, in get_tokenizer encoding = get_encoding(name=encoding_name) File "/home/natan/.local/lib/python3.10/site-packages/whisper/tokenizer.py", line 355, in get_encoding pat_str=gpt2()["pat_str"], File "/home/natan/.local/lib/python3.10/site-packages/tiktoken_ext/openai_public.py", line 11, in gpt2 mergeable_ranks = data_gym_to_mergeable_bpe_ranks( File "/home/natan/.local/lib/python3.10/site-packages/tiktoken/load.py", line 83, in data_gym_to_mergeable_bpe_ranks for first, second in bpe_merges: ValueError: too many values to unpack (expected 2)

[natan2525]

Fixed it by replacing vocab_bpe_file and encoder_json_file in openai_public.py (tiktoken_ext) with local paths. Files were downloaded manually via browser. Debugging in Pycharm revealed that response was some kind of api auth error ("Server failed to authenticate the request. Make sure the value of Authorization header is formed correctly including the signature."). I'll try to open issue about it.