From 3bc0efcc1442a722dd00aa30857688e1252b07be Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 22 七月 2024 20:05:03 +0800
Subject: [PATCH] python runtime
---
runtime/python/libtorch/funasr_torch/sensevoice_bin.py | 13 ++++++-------
1 files changed, 6 insertions(+), 7 deletions(-)
diff --git a/runtime/python/libtorch/funasr_torch/sensevoice_bin.py b/runtime/python/libtorch/funasr_torch/sensevoice_bin.py
index 19ed37d..2f66f4e 100644
--- a/runtime/python/libtorch/funasr_torch/sensevoice_bin.py
+++ b/runtime/python/libtorch/funasr_torch/sensevoice_bin.py
@@ -33,14 +33,13 @@
self,
model_dir: Union[str, Path] = None,
batch_size: int = 1,
- device_id: Union[str, int] = "-1",
plot_timestamp_to: str = "",
quantize: bool = False,
intra_op_num_threads: int = 4,
cache_dir: str = None,
**kwargs,
):
-
+ self.device = kwargs.get("device", "cpu")
if not Path(model_dir).exists():
try:
from modelscope.hub.snapshot_download import snapshot_download
@@ -99,10 +98,10 @@
end_idx = min(waveform_nums, beg_idx + self.batch_size)
feats, feats_len = self.extract_feat(waveform_list[beg_idx:end_idx])
ctc_logits, encoder_out_lens = self.ort_infer(
- torch.Tensor(feats),
- torch.Tensor(feats_len),
- torch.tensor([language]),
- torch.tensor([textnorm]),
+ torch.Tensor(feats).to(self.device),
+ torch.Tensor(feats_len).to(self.device),
+ torch.tensor([language]).to(self.device),
+ torch.tensor([textnorm]).to(self.device),
)
# support batch_size=1 only currently
x = ctc_logits[0, : encoder_out_lens[0].item(), :]
@@ -113,7 +112,7 @@
token_int = yseq[mask].tolist()
if tokenizer is not None:
- asr_res.append(tokenizer.decode(token_int))
+ asr_res.append(self.tokenizer.decode(token_int))
else:
asr_res.append(token_int)
return asr_res
--
Gitblit v1.9.1