Add --threads option to transcribe (#278)

* Add --threads option to transcribe

Torch on CPU uses by default number_of_cores/2. This option allows to
override this default.

* Update transcribe.py

Co-authored-by: Jong Wook Kim <ilikekjw@gmail.com>

whisper/transcribe.py

@@ -261,7 +261,7 @@ def cli():
     parser.add_argument("--best_of", type=optional_int, default=5, help="number of candidates when sampling with non-zero temperature")
     parser.add_argument("--beam_size", type=optional_int, default=5, help="number of beams in beam search, only applicable when temperature is zero")
     parser.add_argument("--patience", type=float, default=None, help="optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (1.0) is equivalent to conventional beam search")
-    parser.add_argument("--length_penalty", type=float, default=None, help="optional token length penalty coefficient (alpha) as in https://arxiv.org/abs/1609.08144, uses simple lengt normalization by default")
+    parser.add_argument("--length_penalty", type=float, default=None, help="optional token length penalty coefficient (alpha) as in https://arxiv.org/abs/1609.08144, uses simple length normalization by default")
 
     parser.add_argument("--suppress_tokens", type=str, default="-1", help="comma-separated list of token ids to suppress during sampling; '-1' will suppress most special characters except common punctuations")
     parser.add_argument("--initial_prompt", type=str, default=None, help="optional text to provide as a prompt for the first window.")
@@ -272,6 +272,7 @@ def cli():
     parser.add_argument("--compression_ratio_threshold", type=optional_float, default=2.4, help="if the gzip compression ratio is higher than this value, treat the decoding as failed")
     parser.add_argument("--logprob_threshold", type=optional_float, default=-1.0, help="if the average log probability is lower than this value, treat the decoding as failed")
     parser.add_argument("--no_speech_threshold", type=optional_float, default=0.6, help="if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence")
+    parser.add_argument("--threads", type=optional_int, default=0, help="number of threads used by torch for CPU inference; supercedes MKL_NUM_THREADS/OMP_NUM_THREADS")
 
     args = parser.parse_args().__dict__
     model_name: str = args.pop("model")
@@ -291,6 +292,10 @@ def cli():
     else:
         temperature = [temperature]
 
+    threads = args.pop("threads")
+    if threads > 0:
+        torch.set_num_threads(threads)
+
     from . import load_model
     model = load_model(model_name, device=device, download_root=model_dir)