From 88c4f4a25df3c171dc0d07efc400f73e6a09e165 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 07 二月 2023 21:43:30 +0800
Subject: [PATCH] export model
---
funasr/export/models/e2e_asr_paraformer.py | 11 ++++++++++-
1 files changed, 10 insertions(+), 1 deletions(-)
diff --git a/funasr/export/models/e2e_asr_paraformer.py b/funasr/export/models/e2e_asr_paraformer.py
index dd87213..8388f4f 100644
--- a/funasr/export/models/e2e_asr_paraformer.py
+++ b/funasr/export/models/e2e_asr_paraformer.py
@@ -63,8 +63,9 @@
decoder_out, _ = self.decoder(enc, enc_len, pre_acoustic_embeds, pre_token_length)
decoder_out = torch.log_softmax(decoder_out, dim=-1)
+ sample_ids = decoder_out.argmax(dim=-1)
- return decoder_out, pre_token_length
+ return decoder_out, sample_ids
# def get_output_size(self):
# return self.model.encoders[0].size
@@ -74,6 +75,14 @@
speech_lengths = torch.tensor([6, 30], dtype=torch.int32)
return (speech, speech_lengths)
+ def get_dummy_inputs_txt(self, txt_file: str = "/mnt/workspace/data_fbank/0207/12345.wav.fea.txt"):
+ import numpy as np
+ fbank = np.loadtxt(txt_file)
+ fbank_lengths = np.array([fbank.shape[0], ], dtype=np.int32)
+ speech = torch.from_numpy(fbank[None, :, :].astype(np.float32))
+ speech_lengths = torch.from_numpy(fbank_lengths.astype(np.int32))
+ return (speech, speech_lengths)
+
def get_input_names(self):
return ['speech', 'speech_lengths']
--
Gitblit v1.9.1