Merge pull request #61 from alibaba-damo-academy/dev_lhn

hnluo

2023-02-05 450ed4f344fc6695336c36c2e4854152454c3d22

Merge pull request #61 from alibaba-damo-academy/dev_lhn

Dev lhn

 funasr/bin/asr_inference.py

@@ -534,6 +534,7 @@
    def _forward(data_path_and_name_and_type,
                 raw_inputs: Union[np.ndarray, torch.Tensor] = None,
                 output_dir_v2: Optional[str] = None,
                 fs: dict = None,
                 param_dict: dict = None,
                 ):
        # 3. Build data-iterator
@@ -544,6 +545,7 @@
        loader = ASRTask.build_streaming_iterator(
            data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,

 funasr/bin/asr_inference_paraformer.py

@@ -579,6 +579,7 @@
            data_path_and_name_and_type,
            raw_inputs: Union[np.ndarray, torch.Tensor] = None,
            output_dir_v2: Optional[str] = None,
            fs: dict = None,
            param_dict: dict = None,
    ):
        # 3. Build data-iterator
@@ -589,6 +590,7 @@
        loader = ASRTask.build_streaming_iterator(
            data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,

 funasr/bin/asr_inference_paraformer_vad_punc.py

@@ -548,6 +548,7 @@
    def _forward(data_path_and_name_and_type,
                 raw_inputs: Union[np.ndarray, torch.Tensor] = None,
                 output_dir_v2: Optional[str] = None,
                 fs: dict = None,
                 param_dict: dict = None,
                 ):
        # 3. Build data-iterator
@@ -558,6 +559,7 @@
        loader = ASRTask.build_streaming_iterator(
            data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            batch_size=1,
            key_file=key_file,
            num_workers=num_workers,

 funasr/bin/asr_inference_uniasr.py

@@ -575,6 +575,7 @@
    def _forward(data_path_and_name_and_type,
                 raw_inputs: Union[np.ndarray, torch.Tensor] = None,
                 output_dir_v2: Optional[str] = None,
                 fs: dict = None,
                 param_dict: dict = None,
                 ):
        # 3. Build data-iterator
@@ -585,6 +586,7 @@
        loader = ASRTask.build_streaming_iterator(
            data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,

 funasr/bin/vad_inference.py

@@ -251,6 +251,7 @@
        dtype: str = "float32",
        seed: int = 0,
        num_workers: int = 1,
        param_dict: dict = None,
        **kwargs,
):
    assert check_argument_types()
@@ -287,6 +288,8 @@
        data_path_and_name_and_type,
        raw_inputs: Union[np.ndarray, torch.Tensor] = None,
        output_dir_v2: Optional[str] = None,
        fs: dict = None,
        param_dict: dict = None,
    ):
        # 3. Build data-iterator
        loader = VADTask.build_streaming_iterator(

 funasr/datasets/iterable_dataset.py

@@ -11,7 +11,6 @@

import kaldiio
import numpy as np
import soundfile
import torch
import torchaudio
from torch.utils.data.dataset import IterableDataset
@@ -101,6 +100,7 @@
                [str, Dict[str, np.ndarray]], Dict[str, np.ndarray]
            ] = None,
            float_dtype: str = "float32",
            fs: dict = None,
            int_dtype: str = "long",
            key_file: str = None,
    ):
@@ -116,6 +116,7 @@
        self.float_dtype = float_dtype
        self.int_dtype = int_dtype
        self.key_file = key_file
        self.fs = fs

        self.debug_info = {}
        non_iterable_list = []
@@ -175,6 +176,15 @@
            _type = self.path_name_type_list[0][2]
            func = DATA_TYPES[_type]
            array = func(value)
            if self.fs is not None and name == "speech":
                audio_fs = self.fs["audio_fs"]
                model_fs = self.fs["model_fs"]
                if audio_fs is not None and model_fs is not None:
                    array = torch.from_numpy(array)
                    array = array.unsqueeze(0)
                    array = torchaudio.transforms.Resample(orig_freq=audio_fs,
                                                   new_freq=model_fs)(array)
                    array = array.squeeze(0).numpy()
            data[name] = array

            if self.preprocess is not None:
@@ -211,6 +221,15 @@
                        f'Not supported audio type: {audio_type}')
            func = DATA_TYPES[_type]
            array = func(value)
            if self.fs is not None and name == "speech":
                audio_fs = self.fs["audio_fs"]
                model_fs = self.fs["model_fs"]
                if audio_fs is not None and model_fs is not None:
                    array = torch.from_numpy(array)
                    array = array.unsqueeze(0)
                    array = torchaudio.transforms.Resample(orig_freq=audio_fs,
                                                           new_freq=model_fs)(array)
                    array = array.squeeze(0).numpy()
            data[name] = array

            if self.preprocess is not None:
@@ -302,6 +321,15 @@
                    func = DATA_TYPES[_type]
                    # Load entry
                    array = func(value)
                    if self.fs is not None and name == "speech":
                        audio_fs = self.fs["audio_fs"]
                        model_fs = self.fs["model_fs"]
                        if audio_fs is not None and model_fs is not None:
                            array = torch.from_numpy(array)
                            array = array.unsqueeze(0)
                            array = torchaudio.transforms.Resample(orig_freq=audio_fs,
                                                                   new_freq=model_fs)(array)
                            array = array.squeeze(0).numpy()
                    data[name] = array
                if self.non_iterable_dataset is not None:
                    # 2.b. Load data from non-iterable dataset
@@ -335,4 +363,3 @@

        if count == 0:
            raise RuntimeError("No iteration")


 funasr/tasks/abs_task.py

@@ -1783,6 +1783,7 @@
            collate_fn,
            key_file: str = None,
            batch_size: int = 1,
            fs: dict = None,
            dtype: str = np.float32,
            num_workers: int = 1,
            allow_variable_data_keys: bool = False,
@@ -1800,6 +1801,7 @@
        dataset = IterableESPnetDataset(
            data_path_and_name_and_type,
            float_dtype=dtype,
            fs=fs,
            preprocess=preprocess_fn,
            key_file=key_file,
        )