verachen/Fun-ASR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add finetune script

Browse Source
This commit is contained in:
pengzhendong
2025-12-24 13:49:09 +08:00
parent 2b79dffe3e
commit 78619da40c
5 changed files with 116 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
model.py
View File

@ -125,7 +125,6 @@ class FunASRNano(nn.Module):
self.use_low_frame_rate = audio_adaptor_conf.get("use_low_frame_rate", False)
self.length_normalized_loss = length_normalized_loss
self.feat_permute = audio_encoder_conf.get("feat_permute", True)
rank = int(os.environ.get("RANK", 0))
logging.info(f"rank: {rank}, model is builded.")
@ -255,12 +254,7 @@ class FunASRNano(nn.Module):
def encode(self, speech, speech_lengths):
# audio encoder
if self.feat_permute:
encoder_out, encoder_out_lens = self.audio_encoder(
speech.permute(0, 2, 1), speech_lengths
)
else:
encoder_out, encoder_out_lens = self.audio_encoder(speech, speech_lengths)
encoder_out, encoder_out_lens = self.audio_encoder(speech, speech_lengths)
return encoder_out, encoder_out_lens
@ -385,9 +379,6 @@ class FunASRNano(nn.Module):
/ 1000
)
if self.feat_permute:
speech = speech.permute(0, 2, 1)
if self.use_low_frame_rate:
olens = 1 + (speech_lengths[0].item() - 3 + 2 * 1) // 2
olens = 1 + (olens - 3 + 2 * 1) // 2