Skip to content
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

Jump to bottom

funasr1.0 update #1278

Merged
merged 1 commit into from
Jan 22, 2024
Merged

funasr1.0 update #1278

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
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ from funasr import AutoModel
# use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh", model_revision="v2.0.2",
vad_model="fsmn-vad", vad_model_revision="v2.0.2",
punc_model="ct-punc-c", punc_model_revision="v2.0.2",
punc_model="ct-punc-c", punc_model_revision="v2.0.3",
# spk_model="cam++", spk_model_revision="v2.0.2",
)
res = model.generate(input=f"{model.model_path}/example/asr_example.wav",
Expand Down
2 changes: 1 addition & 1 deletion README_zh.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@ from funasr import AutoModel
# use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh", model_revision="v2.0.2",
vad_model="fsmn-vad", vad_model_revision="v2.0.2",
punc_model="ct-punc-c", punc_model_revision="v2.0.2",
punc_model="ct-punc-c", punc_model_revision="v2.0.3",
# spk_model="cam++", spk_model_revision="v2.0.2",
)
res = model.generate(input=f"{model.model_path}/example/asr_example.wav",
Expand Down
2 changes: 1 addition & 1 deletion examples/industrial_data_pretraining/bicif_paraformer/demo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
vad_model_revision="v2.0.2",
punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
punc_model_revision="v2.0.2",
punc_model_revision="v2.0.3",
spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
spk_model_revision="v2.0.2",
)
Expand Down
2 changes: 1 addition & 1 deletion examples/industrial_data_pretraining/bicif_paraformer/infer.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ model_revision="v2.0.2"
vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
vad_model_revision="v2.0.2"
punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
punc_model_revision="v2.0.2"
punc_model_revision="v2.0.3"
spk_model="damo/speech_campplus_sv_zh-cn_16k-common"
spk_model_revision="v2.0.2"

Expand Down
2 changes: 1 addition & 1 deletion examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
vad_model_revision="v2.0.2",
punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
punc_model_revision="v2.0.2",
punc_model_revision="v2.0.3",
spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
spk_model_revision="v2.0.2"
)
Expand Down
2 changes: 1 addition & 1 deletion examples/industrial_data_pretraining/paraformer-zh-spk/infer.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ model_revision="v2.0.2"
vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
vad_model_revision="v2.0.2"
punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
punc_model_revision="v2.0.2"
punc_model_revision="v2.0.3"
spk_model="damo/speech_campplus_sv_zh-cn_16k-common"
spk_model_revision="v2.0.2"

Expand Down
7 changes: 6 additions & 1 deletion examples/industrial_data_pretraining/paraformer/demo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,12 @@

from funasr import AutoModel

model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.2")
model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.3",
# vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
# vad_model_revision="v2.0.2",
# punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
# punc_model_revision="v2.0.3",
)

res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
print(res)
Expand Down
2 changes: 1 addition & 1 deletion examples/industrial_data_pretraining/seaco_paraformer/demo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
vad_model_revision="v2.0.2",
punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
punc_model_revision="v2.0.2",
punc_model_revision="v2.0.3",
spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
spk_model_revision="v2.0.2",
)
Expand Down
2 changes: 1 addition & 1 deletion examples/industrial_data_pretraining/seaco_paraformer/infer.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ model_revision="v2.0.2"
vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
vad_model_revision="v2.0.2"
punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
punc_model_revision="v2.0.2"
punc_model_revision="v2.0.3"

python funasr/bin/inference.py \
+model=${model} \
Expand Down
2 changes: 1 addition & 1 deletion funasr/auto/auto_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -391,7 +391,7 @@ def inference_with_vad(self, input, input_len=None, **cfg):
if self.punc_model is not None:
self.punc_kwargs.update(cfg)
punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg)
result["text_with_punc"] = punc_res[0]["text"]
result["text"] = punc_res[0]["text"]

# speaker embedding cluster after resorted
if self.spk_model is not None:
Expand Down
2 changes: 1 addition & 1 deletion funasr/models/paraformer/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -451,7 +451,7 @@ def inference(self,
self.nbest = kwargs.get("nbest", 1)

meta_data = {}
if isinstance(data_in, torch.Tensor): # fbank
if isinstance(data_in, torch.Tensor) and kwargs.get("data_type", "sound") == "fbank": # fbank
speech, speech_lengths = data_in, data_lengths
if len(speech.shape) < 3:
speech = speech[None, :, :]
Expand Down
Loading