mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 01:52:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix librispeech CI test errors

Browse Source
This commit is contained in:
k2-fsa 2025-06-30 20:36:21 +08:00
parent fe36fcc25c
commit ffe2f16b1d
24 changed files with 66 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/scripts/docker/generate_build_matrix.py vendored
View File

@ -91,7 +91,7 @@ def get_matrix(min_torch_version, specified_torch_version, specified_python_vers
matrix = []
for p in python_version:
for t in torch_version:
if min_torch_version and version_gt(min_torch_version, t):
if min_torch_version and version_ge(min_torch_version, t):
continue
# torchaudio <= 1.13.x supports only python <= 3.10

2
.github/workflows/librispeech.yml vendored
View File

@ -30,7 +30,7 @@ jobs:
run: |
# outputting for debugging purposes
python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10"
MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10")
MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10" --min-torch-version "2.6.0")
echo "::set-output name=matrix::${MATRIX}"
librispeech:
needs: generate_build_matrix

3
.github/workflows/test.yml vendored
View File

@ -30,7 +30,8 @@ jobs:
id: set-matrix
run: |
# outputting for debugging purposes
MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py --min-torch-version "2.3")
python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10"
MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10")
echo "::set-output name=matrix::${MATRIX}"
test:
needs: generate_build_matrix

3
.github/workflows/yesno.yml vendored
View File

@ -31,7 +31,8 @@ jobs:
run: |
# outputting for debugging purposes
python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10"
MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10")
# MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10")
MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py --python-version "3.10" --min-torch-version "2.5.0")
echo "::set-output name=matrix::${MATRIX}"
yesno:
needs: generate_build_matrix

8
egs/librispeech/ASR/pruned_transducer_stateless7_ctc/ctc_decode.py
View File

@ -633,7 +633,9 @@ def main():
H = None
bpe_model = None
HLG = k2.Fsa.from_dict(
torch.load(f"{params.lang_dir}/HLG.pt", map_location=device)
torch.load(
f"{params.lang_dir}/HLG.pt", map_location=device, weights_only=False
)
)
assert HLG.requires_grad is False
@ -672,7 +674,9 @@ def main():
torch.save(G.as_dict(), params.lm_dir / "G_4_gram.pt")
else:
logging.info("Loading pre-compiled G_4_gram.pt")
d = torch.load(params.lm_dir / "G_4_gram.pt", map_location=device)
d = torch.load(
params.lm_dir / "G_4_gram.pt", map_location=device, weights_only=False
)
G = k2.Fsa.from_dict(d)
if params.decoding_method == "whole-lattice-rescoring":

2
egs/librispeech/ASR/pruned_transducer_stateless7_ctc/decode.py
View File

@ -786,7 +786,7 @@ def main():
lg_filename = params.lang_dir / "LG.pt"
logging.info(f"Loading {lg_filename}")
decoding_graph = k2.Fsa.from_dict(
torch.load(lg_filename, map_location=device)
torch.load(lg_filename, map_location=device, weights_only=False)
)
decoding_graph.scores *= params.ngram_lm_scale
else:

8
egs/librispeech/ASR/pruned_transducer_stateless7_ctc/jit_pretrained_ctc.py
View File

@ -347,7 +347,9 @@ def main():
"whole-lattice-rescoring",
]:
logging.info(f"Loading HLG from {params.HLG}")
HLG = k2.Fsa.from_dict(torch.load(params.HLG, map_location="cpu"))
HLG = k2.Fsa.from_dict(
torch.load(params.HLG, map_location="cpu", weights_only=False)
)
HLG = HLG.to(device)
if not hasattr(HLG, "lm_scores"):
# For whole-lattice-rescoring and attention-decoder
@ -358,7 +360,9 @@ def main():
"whole-lattice-rescoring",
]:
logging.info(f"Loading G from {params.G}")
G = k2.Fsa.from_dict(torch.load(params.G, map_location="cpu"))
G = k2.Fsa.from_dict(
torch.load(params.G, map_location="cpu", weights_only=False)
)
G = G.to(device)
if params.method == "whole-lattice-rescoring":
# Add epsilon self-loops to G as we will compose

2
egs/librispeech/ASR/pruned_transducer_stateless7_ctc/pretrained.py
View File

@ -247,7 +247,7 @@ def main():
num_param = sum([p.numel() for p in model.parameters()])
logging.info(f"Number of model parameters: {num_param}")
checkpoint = torch.load(args.checkpoint, map_location="cpu")
checkpoint = torch.load(args.checkpoint, map_location="cpu", weights_only=False)
model.load_state_dict(checkpoint["model"], strict=False)
model.to(device)
model.eval()

2
egs/librispeech/ASR/pruned_transducer_stateless7_ctc/pretrained_ctc.py
View File

@ -286,7 +286,7 @@ def main():
num_param = sum([p.numel() for p in model.parameters()])
logging.info(f"Number of model parameters: {num_param}")
checkpoint = torch.load(args.checkpoint, map_location="cpu")
checkpoint = torch.load(args.checkpoint, map_location="cpu", weights_only=False)
model.load_state_dict(checkpoint["model"], strict=False)
model.to(device)
model.eval()

2
egs/librispeech/ASR/pruned_transducer_stateless7_streaming/decode.py
View File

@ -936,7 +936,7 @@ def main():
lg_filename = params.lang_dir / "LG.pt"
logging.info(f"Loading {lg_filename}")
decoding_graph = k2.Fsa.from_dict(
torch.load(lg_filename, map_location=device)
torch.load(lg_filename, map_location=device, weights_only=False)
)
decoding_graph.scores *= params.ngram_lm_scale
else:

2
egs/librispeech/ASR/pruned_transducer_stateless7_streaming/pretrained.py
View File

@ -247,7 +247,7 @@ def main():
num_param = sum([p.numel() for p in model.parameters()])
logging.info(f"Number of model parameters: {num_param}")
checkpoint = torch.load(args.checkpoint, map_location="cpu")
checkpoint = torch.load(args.checkpoint, map_location="cpu", weights_only=False)
model.load_state_dict(checkpoint["model"], strict=False)
model.to(device)
model.eval()

8
egs/librispeech/ASR/zipformer/ctc_decode.py
View File

@ -947,7 +947,9 @@ def main():
H = None
bpe_model = None
HLG = k2.Fsa.from_dict(
torch.load(f"{params.lang_dir}/HLG.pt", map_location=device)
torch.load(
f"{params.lang_dir}/HLG.pt", map_location=device, weights_only=False
)
)
assert HLG.requires_grad is False
@ -987,7 +989,9 @@ def main():
torch.save(G.as_dict(), params.lm_dir / "G_4_gram.pt")
else:
logging.info("Loading pre-compiled G_4_gram.pt")
d = torch.load(params.lm_dir / "G_4_gram.pt", map_location=device)
d = torch.load(
params.lm_dir / "G_4_gram.pt", map_location=device, weights_only=False
)
G = k2.Fsa.from_dict(d)
if params.decoding_method in [

2
egs/librispeech/ASR/zipformer/decode.py
View File

@ -1013,7 +1013,7 @@ def main():
lg_filename = params.lang_dir / "LG.pt"
logging.info(f"Loading {lg_filename}")
decoding_graph = k2.Fsa.from_dict(
torch.load(lg_filename, map_location=device)
torch.load(lg_filename, map_location=device, weights_only=False)
)
decoding_graph.scores *= params.ngram_lm_scale
else:

2
egs/librispeech/ASR/zipformer/decode_gigaspeech.py
View File

@ -1049,7 +1049,7 @@ def main():
lg_filename = params.lang_dir / "LG.pt"
logging.info(f"Loading {lg_filename}")
decoding_graph = k2.Fsa.from_dict(
torch.load(lg_filename, map_location=device)
torch.load(lg_filename, map_location=device, weights_only=False)
)
decoding_graph.scores *= params.ngram_lm_scale
else:

2
egs/librispeech/ASR/zipformer/finetune.py
View File

@ -765,7 +765,7 @@ def load_model_params(
"""
logging.info(f"Loading checkpoint from {ckpt}")
checkpoint = torch.load(ckpt, map_location="cpu")
checkpoint = torch.load(ckpt, map_location="cpu", weights_only=False)
# if module list is empty, load the whole model from ckpt
if not init_modules:

8
egs/librispeech/ASR/zipformer/jit_pretrained_ctc.py
View File

@ -346,7 +346,9 @@ def main():
"whole-lattice-rescoring",
]:
logging.info(f"Loading HLG from {params.HLG}")
HLG = k2.Fsa.from_dict(torch.load(params.HLG, map_location="cpu"))
HLG = k2.Fsa.from_dict(
torch.load(params.HLG, map_location="cpu", weights_only=False)
)
HLG = HLG.to(device)
if not hasattr(HLG, "lm_scores"):
# For whole-lattice-rescoring and attention-decoder
@ -357,7 +359,9 @@ def main():
"whole-lattice-rescoring",
]:
logging.info(f"Loading G from {params.G}")
G = k2.Fsa.from_dict(torch.load(params.G, map_location="cpu"))
G = k2.Fsa.from_dict(
torch.load(params.G, map_location="cpu", weights_only=False)
)
G = G.to(device)
if params.method == "whole-lattice-rescoring":
# Add epsilon self-loops to G as we will compose

2
egs/librispeech/ASR/zipformer/pretrained.py
View File

@ -289,7 +289,7 @@ def main():
num_param = sum([p.numel() for p in model.parameters()])
logging.info(f"Number of model parameters: {num_param}")
checkpoint = torch.load(args.checkpoint, map_location="cpu")
checkpoint = torch.load(args.checkpoint, map_location="cpu", weights_only=False)
model.load_state_dict(checkpoint["model"], strict=False)
model.to(device)
model.eval()

10
egs/librispeech/ASR/zipformer/pretrained_ctc.py
View File

@ -305,7 +305,7 @@ def main():
num_param = sum([p.numel() for p in model.parameters()])
logging.info(f"Number of model parameters: {num_param}")
checkpoint = torch.load(args.checkpoint, map_location="cpu")
checkpoint = torch.load(args.checkpoint, map_location="cpu", weights_only=False)
model.load_state_dict(checkpoint["model"], strict=False)
model.to(device)
model.eval()
@ -389,7 +389,9 @@ def main():
"whole-lattice-rescoring",
]:
logging.info(f"Loading HLG from {params.HLG}")
HLG = k2.Fsa.from_dict(torch.load(params.HLG, map_location="cpu"))
HLG = k2.Fsa.from_dict(
torch.load(params.HLG, map_location="cpu", weights_only=False)
)
HLG = HLG.to(device)
if not hasattr(HLG, "lm_scores"):
# For whole-lattice-rescoring and attention-decoder
@ -400,7 +402,9 @@ def main():
"whole-lattice-rescoring",
]:
logging.info(f"Loading G from {params.G}")
G = k2.Fsa.from_dict(torch.load(params.G, map_location="cpu"))
G = k2.Fsa.from_dict(
torch.load(params.G, map_location="cpu", weights_only=False)
)
G = G.to(device)
if params.method == "whole-lattice-rescoring":
# Add epsilon self-loops to G as we will compose

8
egs/librispeech/ASR/zipformer_ctc/decode.py
View File

@ -679,7 +679,9 @@ def main():
H = None
bpe_model = None
HLG = k2.Fsa.from_dict(
torch.load(f"{params.lang_dir}/HLG.pt", map_location=device)
torch.load(
f"{params.lang_dir}/HLG.pt", map_location=device, weights_only=False
)
)
assert HLG.requires_grad is False
@ -719,7 +721,9 @@ def main():
torch.save(G.as_dict(), params.lm_dir / "G_4_gram.pt")
else:
logging.info("Loading pre-compiled G_4_gram.pt")
d = torch.load(params.lm_dir / "G_4_gram.pt", map_location=device)
d = torch.load(
params.lm_dir / "G_4_gram.pt", map_location=device, weights_only=False
)
G = k2.Fsa.from_dict(d)
if params.method in [

2
egs/yesno/ASR/local/compile_hlg.py
View File

@ -47,7 +47,7 @@ def compile_HLG(lang_dir: str) -> k2.Fsa:
max_token_id = max(lexicon.tokens)
logging.info(f"Building ctc_topo. max_token_id: {max_token_id}")
H = k2.ctc_topo(max_token_id)
L = k2.Fsa.from_dict(torch.load(f"{lang_dir}/L_disambig.pt"))
L = k2.Fsa.from_dict(torch.load(f"{lang_dir}/L_disambig.pt", weights_only=False))
logging.info("Loading G.fst.txt")
with open("data/lm/G.fst.txt") as f:

4
egs/yesno/ASR/tdnn/decode.py
View File

@ -271,7 +271,9 @@ def main():
logging.info(f"device: {device}")
HLG = k2.Fsa.from_dict(torch.load(f"{params.lang_dir}/HLG.pt", map_location="cpu"))
HLG = k2.Fsa.from_dict(
torch.load(f"{params.lang_dir}/HLG.pt", map_location="cpu", weights_only=False)
)
HLG = HLG.to(device)
assert HLG.requires_grad is False

4
egs/yesno/ASR/tdnn/jit_pretrained.py
View File

@ -131,7 +131,9 @@ def main():
model.to(device)
logging.info(f"Loading HLG from {params.HLG}")
HLG = k2.Fsa.from_dict(torch.load(params.HLG, map_location="cpu"))
HLG = k2.Fsa.from_dict(
torch.load(params.HLG, map_location="cpu", weights_only=False)
)
HLG = HLG.to(device)
logging.info("Constructing Fbank computer")

4
egs/yesno/ASR/tdnn/onnx_pretrained.py
View File

@ -176,7 +176,9 @@ def main():
model = OnnxModel(params.nn_model)
logging.info(f"Loading HLG from {args.HLG}")
HLG = k2.Fsa.from_dict(torch.load(params.HLG, map_location="cpu"))
HLG = k2.Fsa.from_dict(
torch.load(params.HLG, map_location="cpu", weights_only=False)
)
HLG = HLG.to(device)
logging.info("Constructing Fbank computer")

6
egs/yesno/ASR/tdnn/pretrained.py
View File

@ -148,13 +148,15 @@ def main():
num_classes=params.num_classes,
)
checkpoint = torch.load(args.checkpoint, map_location="cpu")
checkpoint = torch.load(args.checkpoint, map_location="cpu", weights_only=False)
model.load_state_dict(checkpoint["model"])
model.to(device)
model.eval()
logging.info(f"Loading HLG from {params.HLG}")
HLG = k2.Fsa.from_dict(torch.load(params.HLG, map_location="cpu"))
HLG = k2.Fsa.from_dict(
torch.load(params.HLG, map_location="cpu", weights_only=False)
)
HLG = HLG.to(device)
logging.info("Constructing Fbank computer")