update

haoneng.lhn

2023-05-31 28cabff45f7bc093edf9a9eb857852bf3445eb1c

update

 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo.py

@@ -1,39 +1,12 @@
import os
import logging
import torch
import soundfile

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger

logger = get_logger(log_level=logging.CRITICAL)
logger.setLevel(logging.CRITICAL)

os.environ["MODELSCOPE_CACHE"] = "./"
inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
    model_revision='v1.0.4'
    model_revision='v1.0.5',
    mode="paraformer_fake_streaming"
)

model_dir = os.path.join(os.environ["MODELSCOPE_CACHE"], "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online")
speech, sample_rate = soundfile.read(os.path.join(model_dir, "example/asr_example.wav"))
speech_length = speech.shape[0]

sample_offset = 0
chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
stride_size =  chunk_size[1] * 960
param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
final_result = ""

for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
    if sample_offset + stride_size >= speech_length - 1:
        stride_size = speech_length - sample_offset
        param_dict["is_final"] = True
    rec_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + stride_size],
                                    param_dict=param_dict)
    if len(rec_result) != 0:
        final_result += rec_result['text']
        print(rec_result)
print(final_result)
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
rec_result = inference_pipeline(audio_in=audio_in)
print(rec_result)

 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online.py

New file
@@ -0,0 +1,40 @@
import os
import logging
import torch
import soundfile

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger

logger = get_logger(log_level=logging.CRITICAL)
logger.setLevel(logging.CRITICAL)

os.environ["MODELSCOPE_CACHE"] = "./"
inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
    model_revision='v1.0.4',
    mode="paraformer_streaming"
)

model_dir = os.path.join(os.environ["MODELSCOPE_CACHE"], "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online")
speech, sample_rate = soundfile.read(os.path.join(model_dir, "example/asr_example.wav"))
speech_length = speech.shape[0]

sample_offset = 0
chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
stride_size =  chunk_size[1] * 960
param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
final_result = ""

for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
    if sample_offset + stride_size >= speech_length - 1:
        stride_size = speech_length - sample_offset
        param_dict["is_final"] = True
    rec_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + stride_size],
                                    param_dict=param_dict)
    if len(rec_result) != 0:
        final_result += rec_result['text']
        print(rec_result)
print(final_result)

 funasr/bin/asr_inference_launch.py

@@ -1618,7 +1618,7 @@
        return inference_uniasr(**kwargs)
    elif mode == "paraformer":
        return inference_paraformer(**kwargs)
    elif mode == "paraformer_online":
    elif mode == "paraformer_fake_streaming":
        return inference_paraformer(**kwargs)
    elif mode == "paraformer_streaming":
        return inference_paraformer_online(**kwargs)

 funasr/models/encoder/sanm_encoder.py

@@ -633,6 +633,8 @@
                self.embed = torch.nn.Linear(input_size, output_size)
        elif input_layer == "pe":
            self.embed = SinusoidalPositionEncoder()
        elif input_layer == "pe_online":
            self.embed = StreamSinusoidalPositionEncoder()
        else:
            raise ValueError("unknown input_layer: " + input_layer)
        self.normalize_before = normalize_before
@@ -818,6 +820,59 @@
            return (xs_pad, intermediate_outs), olens, None
        return xs_pad, olens, None

    def _add_overlap_chunk(self, feats: np.ndarray, cache: dict = {}):
        if len(cache) == 0:
            return feats
        cache["feats"] = to_device(cache["feats"], device=feats.device)
        overlap_feats = torch.cat((cache["feats"], feats), dim=1)
        cache["feats"] = overlap_feats[:, -(cache["chunk_size"][0] + cache["chunk_size"][2]):, :]
        return overlap_feats

    def forward_chunk(self,
                      xs_pad: torch.Tensor,
                      ilens: torch.Tensor,
                      cache: dict = None,
                      ctc: CTC = None,
                      ):
        xs_pad *= self.output_size() ** 0.5
        if self.embed is None:
            xs_pad = xs_pad
        else:
            xs_pad = self.embed(xs_pad, cache)
        if cache["tail_chunk"]:
            xs_pad = to_device(cache["feats"], device=xs_pad.device)
        else:
            xs_pad = self._add_overlap_chunk(xs_pad, cache)
        encoder_outs = self.encoders0(xs_pad, None, None, None, None)
        xs_pad, masks = encoder_outs[0], encoder_outs[1]
        intermediate_outs = []
        if len(self.interctc_layer_idx) == 0:
            encoder_outs = self.encoders(xs_pad, None, None, None, None)
            xs_pad, masks = encoder_outs[0], encoder_outs[1]
        else:
            for layer_idx, encoder_layer in enumerate(self.encoders):
                encoder_outs = encoder_layer(xs_pad, None, None, None, None)
                xs_pad, masks = encoder_outs[0], encoder_outs[1]
                if layer_idx + 1 in self.interctc_layer_idx:
                    encoder_out = xs_pad

                    # intermediate outputs are also normalized
                    if self.normalize_before:
                        encoder_out = self.after_norm(encoder_out)

                    intermediate_outs.append((layer_idx + 1, encoder_out))

                    if self.interctc_use_conditioning:
                        ctc_out = ctc.softmax(encoder_out)
                        xs_pad = xs_pad + self.conditioning_layer(ctc_out)

        if self.normalize_before:
            xs_pad = self.after_norm(xs_pad)

        if len(intermediate_outs) > 0:
            return (xs_pad, intermediate_outs), None, None
        return xs_pad, ilens, None

    def gen_tf2torch_map_dict(self):
        tensor_name_prefix_torch = self.tf2torch_tensor_name_prefix_torch
        tensor_name_prefix_tf = self.tf2torch_tensor_name_prefix_tf