Skip to content

return wav_path as utt id #30

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pengzhendong wants to merge 1 commit into
base: main
Choose a base branch
from
Open

return wav_path as utt id #30

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,6 +118,7 @@ def __getitem__(self, i) -> Dict[str, torch.Tensor]:
ctc_ids = ctc_tokens['input_ids'][0]
ctc_ids_len = ctc_tokens['attention_mask'].sum().item()
ret = {
'wav': msg['wav'],
'input_ids': input_ids,
'attention_mask': attention_mask,
'mel': mel,
Expand Down
4 changes: 2 additions & 2 deletions recognize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,9 +60,9 @@ def main():
text = tokenizer.batch_decode(generated_ids,
skip_special_tokens=True)
print(text)
for t in text:
for wav, t in zip(item['wav'], text):
t = t.replace('\n', ' ')
fid.write(t + '\n')
fid.write(wav + ' ' + t + '\n')
sys.stdout.flush()
fid.close()

Expand Down
5 changes: 4 additions & 1 deletion speech_llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
# Copyright (c) 2025 Binbin Zhang(binbzha@qq.com)

import math
from typing import Optional
from typing import List, Optional
from dataclasses import dataclass, field

import safetensors
Expand Down Expand Up @@ -148,6 +148,7 @@ def get_speech_embeddings(self, mel, mel_len):
@torch.autocast(device_type="cuda", dtype=torch.bfloat16)
def forward(
self,
wav: List[str] = None,
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.Tensor] = None,
labels: Optional[torch.LongTensor] = None,
Expand Down Expand Up @@ -181,6 +182,7 @@ def forward(
@torch.autocast(device_type="cuda", dtype=torch.bfloat16)
def generate(
self,
wav: List[str] = None,
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.Tensor] = None,
mel: torch.LongTensor = None,
Expand All @@ -207,6 +209,7 @@ def generate(
@torch.autocast(device_type="cuda", dtype=torch.bfloat16)
def decode_ctc(
self,
wav: List[str] = None,
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.Tensor] = None,
mel: torch.LongTensor = None,
Expand Down