From af1c0d0e30fca785858560ce4ffaf38302e0e43c Mon Sep 17 00:00:00 2001
From: 维石 <shixian.shi@alibaba-inc.com>
Date: 星期五, 26 七月 2024 10:19:32 +0800
Subject: [PATCH] bug fix
---
runtime/python/libtorch/funasr_torch/sensevoice_bin.py | 18 +++++++++++-------
1 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/runtime/python/libtorch/funasr_torch/sensevoice_bin.py b/runtime/python/libtorch/funasr_torch/sensevoice_bin.py
index 8de1c54..4f79340 100644
--- a/runtime/python/libtorch/funasr_torch/sensevoice_bin.py
+++ b/runtime/python/libtorch/funasr_torch/sensevoice_bin.py
@@ -170,15 +170,19 @@
torch.tensor(_language_list).to(self.device),
torch.tensor(_textnorm_list).to(self.device),
)
- # support batch_size=1 only currently
- x = ctc_logits[0, : encoder_out_lens[0].item(), :]
- yseq = x.argmax(dim=-1)
- yseq = torch.unique_consecutive(yseq, dim=-1)
+ for b in range(feats.shape[0]):
+ # back to torch.Tensor
+ if isinstance(ctc_logits, np.ndarray):
+ ctc_logits = torch.from_numpy(ctc_logits).float()
+ # support batch_size=1 only currently
+ x = ctc_logits[b, : encoder_out_lens[b].item(), :]
+ yseq = x.argmax(dim=-1)
+ yseq = torch.unique_consecutive(yseq, dim=-1)
- mask = yseq != self.blank_id
- token_int = yseq[mask].tolist()
+ mask = yseq != self.blank_id
+ token_int = yseq[mask].tolist()
- asr_res.append(self.tokenizer.decode(token_int))
+ asr_res.append(self.tokenizer.decode(token_int))
return asr_res
--
Gitblit v1.9.1