From 3e8159e5b0f6e7e96d4e6ca1f4b4d8ccb151ace5 Mon Sep 17 00:00:00 2001
From: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 20 七月 2023 18:43:38 +0800
Subject: [PATCH] add lora finetune code
---
funasr/bin/asr_inference_launch.py | 141 +++++++++++++++++++++++++++++-----------------
1 files changed, 88 insertions(+), 53 deletions(-)
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 5740f92..3ad0891 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -255,8 +255,10 @@
if param_dict is not None:
hotword_list_or_file = param_dict.get('hotword')
export_mode = param_dict.get("export_mode", False)
+ clas_scale = param_dict.get('clas_scale', 1.0)
else:
hotword_list_or_file = None
+ clas_scale = 1.0
if kwargs.get("device", None) == "cpu":
ngpu = 0
@@ -289,6 +291,7 @@
penalty=penalty,
nbest=nbest,
hotword_list_or_file=hotword_list_or_file,
+ clas_scale=clas_scale,
)
speech2text = Speech2TextParaformer(**speech2text_kwargs)
@@ -436,6 +439,7 @@
logging.info(rtf_avg)
if writer is not None:
ibest_writer["rtf"]["rtf_avf"] = rtf_avg
+ torch.cuda.empty_cache()
return asr_result_list
return _forward
@@ -617,10 +621,27 @@
sorted_data = sorted(data_with_index, key=lambda x: x[0][1] - x[0][0])
results_sorted = []
+ if not len(sorted_data):
+ key = keys[0]
+ # no active segments after VAD
+ if writer is not None:
+ # Write empty results
+ ibest_writer["token"][key] = ""
+ ibest_writer["token_int"][key] = ""
+ ibest_writer["vad"][key] = ""
+ ibest_writer["text"][key] = ""
+ ibest_writer["text_with_punc"][key] = ""
+ if use_timestamp:
+ ibest_writer["time_stamp"][key] = ""
+
+ logging.info("decoding, utt: {}, empty speech".format(key))
+ continue
+
batch_size_token_ms = batch_size_token*60
if speech2text.device == "cpu":
batch_size_token_ms = 0
- batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])
+ if len(sorted_data) > 0 and len(sorted_data[0]) > 0:
+ batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])
batch_size_token_ms_cum = 0
beg_idx = 0
@@ -710,6 +731,7 @@
ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed)
logging.info("decoding, utt: {}, predictions: {}".format(key, text_postprocessed_punc))
+ torch.cuda.empty_cache()
return asr_result_list
return _forward
@@ -1252,27 +1274,27 @@
nbest: int,
num_workers: int,
log_level: Union[int, str],
- data_path_and_name_and_type: Sequence[Tuple[str, str, str]],
+ # data_path_and_name_and_type: Sequence[Tuple[str, str, str]],
asr_train_config: Optional[str],
asr_model_file: Optional[str],
- cmvn_file: Optional[str],
- beam_search_config: Optional[dict],
- lm_train_config: Optional[str],
- lm_file: Optional[str],
- model_tag: Optional[str],
- token_type: Optional[str],
- bpemodel: Optional[str],
- key_file: Optional[str],
- allow_variable_data_keys: bool,
- quantize_asr_model: Optional[bool],
- quantize_modules: Optional[List[str]],
- quantize_dtype: Optional[str],
- streaming: Optional[bool],
- simu_streaming: Optional[bool],
- chunk_size: Optional[int],
- left_context: Optional[int],
- right_context: Optional[int],
- display_partial_hypotheses: bool,
+ cmvn_file: Optional[str] = None,
+ beam_search_config: Optional[dict] = None,
+ lm_train_config: Optional[str] = None,
+ lm_file: Optional[str] = None,
+ model_tag: Optional[str] = None,
+ token_type: Optional[str] = None,
+ bpemodel: Optional[str] = None,
+ key_file: Optional[str] = None,
+ allow_variable_data_keys: bool = False,
+ quantize_asr_model: Optional[bool] = False,
+ quantize_modules: Optional[List[str]] = None,
+ quantize_dtype: Optional[str] = "float16",
+ streaming: Optional[bool] = False,
+ simu_streaming: Optional[bool] = False,
+ chunk_size: Optional[int] = 16,
+ left_context: Optional[int] = 16,
+ right_context: Optional[int] = 0,
+ display_partial_hypotheses: bool = False,
**kwargs,
) -> None:
"""Transducer model inference.
@@ -1349,7 +1371,10 @@
left_context=left_context,
right_context=right_context,
)
- speech2text = Speech2TextTransducer(**speech2text_kwargs)
+ speech2text = Speech2TextTransducer.from_pretrained(
+ model_tag=model_tag,
+ **speech2text_kwargs,
+ )
def _forward(data_path_and_name_and_type,
raw_inputs: Union[np.ndarray, torch.Tensor] = None,
@@ -1368,47 +1393,55 @@
key_file=key_file,
num_workers=num_workers,
)
+ asr_result_list = []
+
+ if output_dir is not None:
+ writer = DatadirWriter(output_dir)
+ else:
+ writer = None
# 4 .Start for-loop
- with DatadirWriter(output_dir) as writer:
- for keys, batch in loader:
- assert isinstance(batch, dict), type(batch)
- assert all(isinstance(s, str) for s in keys), keys
+ for keys, batch in loader:
+ assert isinstance(batch, dict), type(batch)
+ assert all(isinstance(s, str) for s in keys), keys
- _bs = len(next(iter(batch.values())))
- assert len(keys) == _bs, f"{len(keys)} != {_bs}"
- batch = {k: v[0] for k, v in batch.items() if not k.endswith("_lengths")}
- assert len(batch.keys()) == 1
+ _bs = len(next(iter(batch.values())))
+ assert len(keys) == _bs, f"{len(keys)} != {_bs}"
+ batch = {k: v[0] for k, v in batch.items() if not k.endswith("_lengths")}
+ assert len(batch.keys()) == 1
- try:
- if speech2text.streaming:
- speech = batch["speech"]
+ try:
+ if speech2text.streaming:
+ speech = batch["speech"]
- _steps = len(speech) // speech2text._ctx
- _end = 0
- for i in range(_steps):
- _end = (i + 1) * speech2text._ctx
+ _steps = len(speech) // speech2text._ctx
+ _end = 0
+ for i in range(_steps):
+ _end = (i + 1) * speech2text._ctx
- speech2text.streaming_decode(
- speech[i * speech2text._ctx: _end], is_final=False
- )
-
- final_hyps = speech2text.streaming_decode(
- speech[_end: len(speech)], is_final=True
+ speech2text.streaming_decode(
+ speech[i * speech2text._ctx: _end], is_final=False
)
- elif speech2text.simu_streaming:
- final_hyps = speech2text.simu_streaming_decode(**batch)
- else:
- final_hyps = speech2text(**batch)
- results = speech2text.hypotheses_to_results(final_hyps)
- except TooShortUttError as e:
- logging.warning(f"Utterance {keys} {e}")
- hyp = Hypothesis(score=0.0, yseq=[], dec_state=None)
- results = [[" ", ["<space>"], [2], hyp]] * nbest
+ final_hyps = speech2text.streaming_decode(
+ speech[_end: len(speech)], is_final=True
+ )
+ elif speech2text.simu_streaming:
+ final_hyps = speech2text.simu_streaming_decode(**batch)
+ else:
+ final_hyps = speech2text(**batch)
- key = keys[0]
- for n, (text, token, token_int, hyp) in zip(range(1, nbest + 1), results):
+ results = speech2text.hypotheses_to_results(final_hyps)
+ except TooShortUttError as e:
+ logging.warning(f"Utterance {keys} {e}")
+ hyp = Hypothesis(score=0.0, yseq=[], dec_state=None)
+ results = [[" ", ["<space>"], [2], hyp]] * nbest
+
+ key = keys[0]
+ for n, (text, token, token_int, hyp) in zip(range(1, nbest + 1), results):
+ item = {'key': key, 'value': text}
+ asr_result_list.append(item)
+ if writer is not None:
ibest_writer = writer[f"{n}best_recog"]
ibest_writer["token"][key] = " ".join(token)
@@ -1418,6 +1451,8 @@
if text is not None:
ibest_writer["text"][key] = text
+ logging.info("decoding, utt: {}, predictions: {}".format(key, text))
+ return asr_result_list
return _forward
--
Gitblit v1.9.1