From 4ac582341c5f88fe30bc47225cf9811cc1233983 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 15 五月 2023 00:32:33 +0800
Subject: [PATCH] inference
---
funasr/bin/asr_inference.py | 74 +------------------------------------
1 files changed, 2 insertions(+), 72 deletions(-)
diff --git a/funasr/bin/asr_inference.py b/funasr/bin/asr_inference.py
index 18f0add..f70382b 100644
--- a/funasr/bin/asr_inference.py
+++ b/funasr/bin/asr_inference.py
@@ -94,7 +94,7 @@
frontend = None
if asr_train_args.frontend is not None and asr_train_args.frontend_conf is not None:
if asr_train_args.frontend=='wav_frontend':
- frontend = WavFrontend(cmvn_file=cmvn_file, **asr_train_args.frontend_conf).eval()
+ frontend = WavFrontend(cmvn_file=cmvn_file, **asr_train_args.frontend_conf)
else:
frontend_class=frontend_choices.get_class(asr_train_args.frontend)
frontend = frontend_class(**asr_train_args.frontend_conf).eval()
@@ -146,13 +146,6 @@
token_list=token_list,
pre_beam_score_key=None if ctc_weight == 1.0 else "full",
)
-
- beam_search.to(device=device, dtype=getattr(torch, dtype)).eval()
- for scorer in scorers.values():
- if isinstance(scorer, torch.nn.Module):
- scorer.to(device=device, dtype=getattr(torch, dtype)).eval()
- logging.info(f"Beam_search: {beam_search}")
- logging.info(f"Decoding device={device}, dtype={dtype}")
# 5. [Optional] Build Text converter: e.g. bpe-sym -> Text
if token_type is None:
@@ -263,70 +256,7 @@
assert check_return_type(results)
return results
-def inference(
- maxlenratio: float,
- minlenratio: float,
- batch_size: int,
- beam_size: int,
- ngpu: int,
- ctc_weight: float,
- lm_weight: float,
- penalty: float,
- log_level: Union[int, str],
- data_path_and_name_and_type,
- asr_train_config: Optional[str],
- asr_model_file: Optional[str],
- cmvn_file: Optional[str] = None,
- raw_inputs: Union[np.ndarray, torch.Tensor] = None,
- lm_train_config: Optional[str] = None,
- lm_file: Optional[str] = None,
- token_type: Optional[str] = None,
- key_file: Optional[str] = None,
- word_lm_train_config: Optional[str] = None,
- bpemodel: Optional[str] = None,
- allow_variable_data_keys: bool = False,
- streaming: bool = False,
- output_dir: Optional[str] = None,
- dtype: str = "float32",
- seed: int = 0,
- ngram_weight: float = 0.9,
- nbest: int = 1,
- num_workers: int = 1,
- mc: bool = False,
- **kwargs,
-):
- inference_pipeline = inference_modelscope(
- maxlenratio=maxlenratio,
- minlenratio=minlenratio,
- batch_size=batch_size,
- beam_size=beam_size,
- ngpu=ngpu,
- ctc_weight=ctc_weight,
- lm_weight=lm_weight,
- penalty=penalty,
- log_level=log_level,
- asr_train_config=asr_train_config,
- asr_model_file=asr_model_file,
- cmvn_file=cmvn_file,
- raw_inputs=raw_inputs,
- lm_train_config=lm_train_config,
- lm_file=lm_file,
- token_type=token_type,
- key_file=key_file,
- word_lm_train_config=word_lm_train_config,
- bpemodel=bpemodel,
- allow_variable_data_keys=allow_variable_data_keys,
- streaming=streaming,
- output_dir=output_dir,
- dtype=dtype,
- seed=seed,
- ngram_weight=ngram_weight,
- nbest=nbest,
- num_workers=num_workers,
- mc=mc,
- **kwargs,
- )
- return inference_pipeline(data_path_and_name_and_type, raw_inputs)
+
def inference_modelscope(
maxlenratio: float,
--
Gitblit v1.9.1