From 447222c00e545906879364c641846f399290dcee Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 25 三月 2024 12:37:35 +0800
Subject: [PATCH] install requirements automatically
---
funasr/models/llm_asr_nar/model.py | 4
funasr/download/download_from_hub.py | 2
examples/industrial_data_pretraining/paraformer/export.py | 2
examples/industrial_data_pretraining/ct_transformer/export.py | 2
examples/industrial_data_pretraining/bicif_paraformer/export.py | 2
examples/common_voice/whisper_lid/demo_funasr.py | 2
examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh | 2
examples/industrial_data_pretraining/monotonic_aligner/demo.sh | 2
examples/industrial_data_pretraining/scama/demo.py | 2
examples/industrial_data_pretraining/paraformer_streaming/export.sh | 2
examples/industrial_data_pretraining/contextual_paraformer/demo.sh | 2
examples/industrial_data_pretraining/paraformer_streaming/demo.py | 2
examples/industrial_data_pretraining/paraformer/infer.sh | 2
examples/industrial_data_pretraining/ct_transformer_streaming/demo.py | 2
examples/industrial_data_pretraining/ct_transformer_streaming/export.py | 2
examples/industrial_data_pretraining/contextual_paraformer/demo.py | 2
examples/industrial_data_pretraining/seaco_paraformer/demo.sh | 6 +-
examples/industrial_data_pretraining/conformer/demo.py | 2
examples/industrial_data_pretraining/bicif_paraformer/demo.py | 6 +-
examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh | 2
examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh | 6 +-
examples/industrial_data_pretraining/bicif_paraformer/export.sh | 2
examples/industrial_data_pretraining/paraformer_streaming/finetune.sh | 2
examples/industrial_data_pretraining/ct_transformer/demo.py | 4
examples/industrial_data_pretraining/bicif_paraformer/finetune.sh | 2
examples/industrial_data_pretraining/paraformer/finetune.sh | 2
examples/industrial_data_pretraining/paraformer_streaming/export.py | 2
examples/industrial_data_pretraining/whisper/infer.sh | 2
examples/common_voice/whisper_lid/demo_modelscope.py | 2
examples/industrial_data_pretraining/paraformer_streaming/demo.sh | 2
examples/industrial_data_pretraining/emotion2vec/demo.py | 4
examples/industrial_data_pretraining/paraformer/demo.py | 8 +-
examples/industrial_data_pretraining/scama/demo.sh | 2
examples/industrial_data_pretraining/uniasr/demo.sh | 2
examples/industrial_data_pretraining/paraformer/export.sh | 2
examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh | 2
examples/industrial_data_pretraining/ct_transformer/export.sh | 2
examples/industrial_data_pretraining/uniasr/demo.py | 4
funasr/models/llm_asr/model.py | 2
examples/industrial_data_pretraining/paraformer-zh-spk/demo.py | 6 +-
examples/industrial_data_pretraining/contextual_paraformer/finetune.sh | 2
funasr/auto/auto_model.py | 6 +-
examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py | 2
examples/industrial_data_pretraining/monotonic_aligner/demo.py | 2
examples/industrial_data_pretraining/fsmn_vad_streaming/export.py | 2
examples/industrial_data_pretraining/bicif_paraformer/demo.sh | 6 +-
examples/industrial_data_pretraining/ct_transformer/demo.sh | 4
examples/industrial_data_pretraining/conformer/demo.sh | 2
examples/industrial_data_pretraining/seaco_paraformer/demo.py | 6 +-
examples/industrial_data_pretraining/ct_transformer_streaming/export.sh | 2
50 files changed, 72 insertions(+), 72 deletions(-)
diff --git a/examples/common_voice/whisper_lid/demo_funasr.py b/examples/common_voice/whisper_lid/demo_funasr.py
index 9af790e..50f4e2a 100644
--- a/examples/common_voice/whisper_lid/demo_funasr.py
+++ b/examples/common_voice/whisper_lid/demo_funasr.py
@@ -12,7 +12,7 @@
"example_ko.mp3",
]
-model = AutoModel(model="iic/speech_whisper-large_lid_multilingual_pytorch", model_revision="v2.0.4")
+model = AutoModel(model="iic/speech_whisper-large_lid_multilingual_pytorch", model_revision="master")
for wav_id in multilingual_wavs:
wav_file = f"{model.model_path}/examples/{wav_id}"
res = model.generate(input=wav_file, data_type="sound", inference_clip_length=250)
diff --git a/examples/common_voice/whisper_lid/demo_modelscope.py b/examples/common_voice/whisper_lid/demo_modelscope.py
index cce389a..e55a972 100644
--- a/examples/common_voice/whisper_lid/demo_modelscope.py
+++ b/examples/common_voice/whisper_lid/demo_modelscope.py
@@ -15,7 +15,7 @@
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
- model='iic/speech_whisper-large_lid_multilingual_pytorch', model_revision="v2.0.4")
+ model='iic/speech_whisper-large_lid_multilingual_pytorch', model_revision="master")
for wav in multilingual_wavs:
rec_result = inference_pipeline(input=wav, inference_clip_length=250)
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/demo.py b/examples/industrial_data_pretraining/bicif_paraformer/demo.py
index c8c4fa7..0b17065 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/bicif_paraformer/demo.py
@@ -6,11 +6,11 @@
from funasr import AutoModel
model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- model_revision="v2.0.4",
+ model_revision="master",
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- vad_model_revision="v2.0.4",
+ vad_model_revision="master",
punc_model="iic/punc_ct-transformer_cn-en-common-vocab471067-large",
- punc_model_revision="v2.0.4",
+ punc_model_revision="master",
# spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
# spk_model_revision="v2.0.2",
)
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/demo.sh b/examples/industrial_data_pretraining/bicif_paraformer/demo.sh
index b6c1d17..fe44734 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/demo.sh
+++ b/examples/industrial_data_pretraining/bicif_paraformer/demo.sh
@@ -1,11 +1,11 @@
model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-vad_model_revision="v2.0.4"
+vad_model_revision="master"
#punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
punc_model="iic/punc_ct-transformer_cn-en-common-vocab471067-large"
-punc_model_revision="v2.0.4"
+punc_model_revision="master"
spk_model="iic/speech_campplus_sv_zh-cn_16k-common"
spk_model_revision="v2.0.2"
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/export.py b/examples/industrial_data_pretraining/bicif_paraformer/export.py
index 28a9e7b..8e45a23 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/export.py
+++ b/examples/industrial_data_pretraining/bicif_paraformer/export.py
@@ -8,7 +8,7 @@
from funasr import AutoModel
model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- model_revision="v2.0.4", device="cpu")
+ model_revision="master", device="cpu")
res = model.export(type="onnx", quantize=False)
print(res)
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/export.sh b/examples/industrial_data_pretraining/bicif_paraformer/export.sh
index b6883b7..cf040ec 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/export.sh
+++ b/examples/industrial_data_pretraining/bicif_paraformer/export.sh
@@ -6,7 +6,7 @@
model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
python -m funasr.bin.export \
++model=${model} \
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh b/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
index 885e5c0..9d251a1 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
@@ -11,7 +11,7 @@
## option 1, download model automatically
model_name_or_model_dir="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
## option 2, download model by git
#local_path_root=${workspace}/modelscope_models
diff --git a/examples/industrial_data_pretraining/conformer/demo.py b/examples/industrial_data_pretraining/conformer/demo.py
index 358a1f8..1abc7a7 100644
--- a/examples/industrial_data_pretraining/conformer/demo.py
+++ b/examples/industrial_data_pretraining/conformer/demo.py
@@ -5,7 +5,7 @@
from funasr import AutoModel
-model = AutoModel(model="iic/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch", model_revision="v2.0.4",
+model = AutoModel(model="iic/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch", model_revision="master",
)
res = model.generate(input="https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav")
diff --git a/examples/industrial_data_pretraining/conformer/demo.sh b/examples/industrial_data_pretraining/conformer/demo.sh
index c259799..9cf6cc5 100644
--- a/examples/industrial_data_pretraining/conformer/demo.sh
+++ b/examples/industrial_data_pretraining/conformer/demo.sh
@@ -1,6 +1,6 @@
model="iic/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/demo.py b/examples/industrial_data_pretraining/contextual_paraformer/demo.py
index 4168a7d..cd93a4f 100755
--- a/examples/industrial_data_pretraining/contextual_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/contextual_paraformer/demo.py
@@ -5,7 +5,7 @@
from funasr import AutoModel
-model = AutoModel(model="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404", model_revision="v2.0.4")
+model = AutoModel(model="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404", model_revision="master")
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
hotword='杈炬懇闄� 榄旀惌')
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/demo.sh b/examples/industrial_data_pretraining/contextual_paraformer/demo.sh
index 987f2ff..e651338 100755
--- a/examples/industrial_data_pretraining/contextual_paraformer/demo.sh
+++ b/examples/industrial_data_pretraining/contextual_paraformer/demo.sh
@@ -1,6 +1,6 @@
model="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
-model_revision="v2.0.4"
+model_revision="master"
python ../../../funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh b/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
index de88968..fe12315 100644
--- a/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
@@ -11,7 +11,7 @@
## option 1, download model automatically
model_name_or_model_dir="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
-model_revision="v2.0.4"
+model_revision="master"
## option 2, download model by git
#local_path_root=${workspace}/modelscope_models
diff --git a/examples/industrial_data_pretraining/ct_transformer/demo.py b/examples/industrial_data_pretraining/ct_transformer/demo.py
index 31755dc..6e6b478 100644
--- a/examples/industrial_data_pretraining/ct_transformer/demo.py
+++ b/examples/industrial_data_pretraining/ct_transformer/demo.py
@@ -5,7 +5,7 @@
from funasr import AutoModel
-model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch", model_revision="v2.0.4")
+model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch", model_revision="master")
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt")
print(res)
@@ -13,7 +13,7 @@
from funasr import AutoModel
-model = AutoModel(model="iic/punc_ct-transformer_cn-en-common-vocab471067-large", model_revision="v2.0.4")
+model = AutoModel(model="iic/punc_ct-transformer_cn-en-common-vocab471067-large", model_revision="master")
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt")
print(res)
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/ct_transformer/demo.sh b/examples/industrial_data_pretraining/ct_transformer/demo.sh
index 56d0bd3..02ee5a8 100644
--- a/examples/industrial_data_pretraining/ct_transformer/demo.sh
+++ b/examples/industrial_data_pretraining/ct_transformer/demo.sh
@@ -1,9 +1,9 @@
#model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
-#model_revision="v2.0.4"
+#model_revision="master"
model="iic/punc_ct-transformer_cn-en-common-vocab471067-large"
-model_revision="v2.0.4"
+model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/ct_transformer/export.py b/examples/industrial_data_pretraining/ct_transformer/export.py
index 8c35670..397bb96 100644
--- a/examples/industrial_data_pretraining/ct_transformer/export.py
+++ b/examples/industrial_data_pretraining/ct_transformer/export.py
@@ -8,7 +8,7 @@
from funasr import AutoModel
model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
- model_revision="v2.0.4")
+ model_revision="master")
res = model.export(type="onnx", quantize=False)
print(res)
diff --git a/examples/industrial_data_pretraining/ct_transformer/export.sh b/examples/industrial_data_pretraining/ct_transformer/export.sh
index a11cda5..5f7e4fb 100644
--- a/examples/industrial_data_pretraining/ct_transformer/export.sh
+++ b/examples/industrial_data_pretraining/ct_transformer/export.sh
@@ -6,7 +6,7 @@
model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
python -m funasr.bin.export \
++model=${model} \
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/demo.py b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.py
index 66cc5c5..14edbe4 100644
--- a/examples/industrial_data_pretraining/ct_transformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.py
@@ -5,7 +5,7 @@
from funasr import AutoModel
-model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727", model_revision="v2.0.4")
+model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727", model_revision="master")
inputs = "璺ㄥ娌虫祦鏄吇鑲叉部宀竱浜烘皯鐨勭敓鍛戒箣婧愰暱鏈熶互鏉ヤ负甯姪涓嬫父鍦板尯闃茬伨鍑忕伨涓柟鎶�鏈汉鍛榺鍦ㄤ笂娓稿湴鍖烘瀬涓烘伓鍔ｇ殑鑷劧鏉′欢涓嬪厠鏈嶅法澶у洶闅剧敋鑷冲啋鐫�鐢熷懡鍗遍櫓|鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦闂涓婄殑鍏冲垏|鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒秥鍑℃槸|涓柟鑳藉仛鐨勬垜浠瑋閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑|浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛瑙勫垝鍜岃璇佸吋椤句笂涓嬫父鐨勫埄鐩�"
vads = inputs.split("|")
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh
index 7124fd5..ad3e3ea 100644
--- a/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh
+++ b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh
@@ -1,6 +1,6 @@
model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727"
-model_revision="v2.0.4"
+model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/export.py b/examples/industrial_data_pretraining/ct_transformer_streaming/export.py
index 47fa08a..2e3b172 100644
--- a/examples/industrial_data_pretraining/ct_transformer_streaming/export.py
+++ b/examples/industrial_data_pretraining/ct_transformer_streaming/export.py
@@ -8,7 +8,7 @@
from funasr import AutoModel
model = AutoModel(model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727",
- model_revision="v2.0.4")
+ model_revision="master")
res = model.export(type="onnx", quantize=False)
print(res)
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/export.sh b/examples/industrial_data_pretraining/ct_transformer_streaming/export.sh
index 118afbb..a47f701 100644
--- a/examples/industrial_data_pretraining/ct_transformer_streaming/export.sh
+++ b/examples/industrial_data_pretraining/ct_transformer_streaming/export.sh
@@ -6,7 +6,7 @@
model="iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727"
-model_revision="v2.0.4"
+model_revision="master"
python -m funasr.bin.export \
++model=${model} \
diff --git a/examples/industrial_data_pretraining/emotion2vec/demo.py b/examples/industrial_data_pretraining/emotion2vec/demo.py
index 510e6e8..50deda3 100644
--- a/examples/industrial_data_pretraining/emotion2vec/demo.py
+++ b/examples/industrial_data_pretraining/emotion2vec/demo.py
@@ -6,9 +6,9 @@
from funasr import AutoModel
# model="iic/emotion2vec_base"
-model = AutoModel(model="iic/emotion2vec_base_finetuned", model_revision="v2.0.4",
+model = AutoModel(model="iic/emotion2vec_base_finetuned", model_revision="master",
# vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- # vad_model_revision="v2.0.4",
+ # vad_model_revision="master",
# vad_kwargs={"max_single_segment_time": 2000},
)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
index 03c01ea..61dce49 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
@@ -6,7 +6,7 @@
from funasr import AutoModel
wav_file = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav"
-model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="v2.0.4")
+model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="master")
res = model.generate(input=wav_file)
print(res)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh
index 8cdf3ed..0248dd0 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh
@@ -1,7 +1,7 @@
model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/export.py b/examples/industrial_data_pretraining/fsmn_vad_streaming/export.py
index 2c8fd4d..f45ddee 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/export.py
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/export.py
@@ -8,7 +8,7 @@
from funasr import AutoModel
-model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="v2.0.4")
+model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="master")
res = model.export(type="onnx", quantize=False)
print(res)
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh b/examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh
index 1a8207a..9143dc3 100644
--- a/examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh
+++ b/examples/industrial_data_pretraining/fsmn_vad_streaming/export.sh
@@ -7,7 +7,7 @@
model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
python -m funasr.bin.export \
++model=${model} \
diff --git a/examples/industrial_data_pretraining/monotonic_aligner/demo.py b/examples/industrial_data_pretraining/monotonic_aligner/demo.py
index 2e76f64..467de1b 100644
--- a/examples/industrial_data_pretraining/monotonic_aligner/demo.py
+++ b/examples/industrial_data_pretraining/monotonic_aligner/demo.py
@@ -5,7 +5,7 @@
from funasr import AutoModel
-model = AutoModel(model="iic/speech_timestamp_prediction-v1-16k-offline", model_revision="v2.0.4")
+model = AutoModel(model="iic/speech_timestamp_prediction-v1-16k-offline", model_revision="master")
res = model.generate(input=("https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
"娆㈣繋澶у鏉ュ埌榄旀惌绀惧尯杩涜浣撻獙"),
diff --git a/examples/industrial_data_pretraining/monotonic_aligner/demo.sh b/examples/industrial_data_pretraining/monotonic_aligner/demo.sh
index ece97ff..649ce70 100644
--- a/examples/industrial_data_pretraining/monotonic_aligner/demo.sh
+++ b/examples/industrial_data_pretraining/monotonic_aligner/demo.sh
@@ -1,6 +1,6 @@
model="iic/speech_timestamp_prediction-v1-16k-offline"
-model_revision="v2.0.4"
+model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
index 6ed0217..523bb3a 100644
--- a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
+++ b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
@@ -6,11 +6,11 @@
from funasr import AutoModel
model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- model_revision="v2.0.4",
+ model_revision="master",
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- vad_model_revision="v2.0.4",
+ vad_model_revision="master",
punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
- punc_model_revision="v2.0.4",
+ punc_model_revision="master",
# spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
# spk_model_revision="v2.0.2"
)
diff --git a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh
index dae1aca..fb0c4d9 100644
--- a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh
+++ b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh
@@ -1,10 +1,10 @@
model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-vad_model_revision="v2.0.4"
+vad_model_revision="master"
punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
-punc_model_revision="v2.0.4"
+punc_model_revision="master"
spk_model="iic/speech_campplus_sv_zh-cn_16k-common"
spk_model_revision="v2.0.2"
diff --git a/examples/industrial_data_pretraining/paraformer/demo.py b/examples/industrial_data_pretraining/paraformer/demo.py
index a39a526..6cef234 100644
--- a/examples/industrial_data_pretraining/paraformer/demo.py
+++ b/examples/industrial_data_pretraining/paraformer/demo.py
@@ -6,12 +6,12 @@
from funasr import AutoModel
model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- model_revision="v2.0.4",
+ model_revision="master",
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- vad_model_revision="v2.0.4",
+ vad_model_revision="master",
vad_kwargs={"max_single_segment_time": 60000},
punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
- punc_model_revision="v2.0.4",
+ punc_model_revision="master",
# spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
# spk_model_revision="v2.0.2",
)
@@ -23,7 +23,7 @@
''' can not use currently
from funasr import AutoFrontend
-frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.4")
+frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="master")
fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)
diff --git a/examples/industrial_data_pretraining/paraformer/export.py b/examples/industrial_data_pretraining/paraformer/export.py
index fce4d77..0c181c1 100644
--- a/examples/industrial_data_pretraining/paraformer/export.py
+++ b/examples/industrial_data_pretraining/paraformer/export.py
@@ -10,7 +10,7 @@
from funasr import AutoModel
model = AutoModel(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- model_revision="v2.0.4")
+ model_revision="master")
res = model.export(type="onnx", quantize=False)
print(res)
diff --git a/examples/industrial_data_pretraining/paraformer/export.sh b/examples/industrial_data_pretraining/paraformer/export.sh
index fc341e7..18d2039 100644
--- a/examples/industrial_data_pretraining/paraformer/export.sh
+++ b/examples/industrial_data_pretraining/paraformer/export.sh
@@ -6,7 +6,7 @@
model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
python -m funasr.bin.export \
diff --git a/examples/industrial_data_pretraining/paraformer/finetune.sh b/examples/industrial_data_pretraining/paraformer/finetune.sh
index 3041ff3..408076b 100644
--- a/examples/industrial_data_pretraining/paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/paraformer/finetune.sh
@@ -10,7 +10,7 @@
## option 1, download model automatically
model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
## option 2, download model by git
#local_path_root=${workspace}/modelscope_models
diff --git a/examples/industrial_data_pretraining/paraformer/infer.sh b/examples/industrial_data_pretraining/paraformer/infer.sh
index aa523e5..0b0f931 100644
--- a/examples/industrial_data_pretraining/paraformer/infer.sh
+++ b/examples/industrial_data_pretraining/paraformer/infer.sh
@@ -9,7 +9,7 @@
output_dir="./outputs/debug"
model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index 9fcee3a..94e5200 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -10,7 +10,7 @@
chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
-model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.4")
+model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="master")
wav_file = os.path.join(model.model_path, "example/asr_example.wav")
res = model.generate(input=wav_file,
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.sh b/examples/industrial_data_pretraining/paraformer_streaming/demo.sh
index c3f7bb4..a316aaf 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.sh
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.sh
@@ -1,6 +1,6 @@
model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
-model_revision="v2.0.4"
+model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/export.py b/examples/industrial_data_pretraining/paraformer_streaming/export.py
index 8e22310..06cec31 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/export.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/export.py
@@ -10,7 +10,7 @@
from funasr import AutoModel
model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online",
- model_revision="v2.0.4")
+ model_revision="master")
res = model.export(type="onnx", quantize=False)
print(res)
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/export.sh b/examples/industrial_data_pretraining/paraformer_streaming/export.sh
index 43e344b..25ac513 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/export.sh
+++ b/examples/industrial_data_pretraining/paraformer_streaming/export.sh
@@ -6,7 +6,7 @@
model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online"
-model_revision="v2.0.4"
+model_revision="master"
python -m funasr.bin.export \
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh b/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
index 2bfb2bf..1e4537a 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
+++ b/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
@@ -10,7 +10,7 @@
## option 1, download model automatically
model_name_or_model_dir="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online"
-model_revision="v2.0.4"
+model_revision="master"
## option 2, download model by git
#local_path_root=${workspace}/modelscope_models
diff --git a/examples/industrial_data_pretraining/scama/demo.py b/examples/industrial_data_pretraining/scama/demo.py
index 1999623..075039a 100644
--- a/examples/industrial_data_pretraining/scama/demo.py
+++ b/examples/industrial_data_pretraining/scama/demo.py
@@ -9,7 +9,7 @@
encoder_chunk_look_back = 0 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 0 #number of encoder chunks to lookback for decoder cross-attention
-model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming", model_revision="v2.0.4")
+model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming", model_revision="master")
cache = {}
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
chunk_size=chunk_size,
diff --git a/examples/industrial_data_pretraining/scama/demo.sh b/examples/industrial_data_pretraining/scama/demo.sh
index c3f7bb4..a316aaf 100644
--- a/examples/industrial_data_pretraining/scama/demo.sh
+++ b/examples/industrial_data_pretraining/scama/demo.sh
@@ -1,6 +1,6 @@
model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
-model_revision="v2.0.4"
+model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/demo.py b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
index 69e9020..c12b279 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
@@ -6,11 +6,11 @@
from funasr import AutoModel
model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- model_revision="v2.0.4",
+ model_revision="master",
# vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- # vad_model_revision="v2.0.4",
+ # vad_model_revision="master",
# punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
- # punc_model_revision="v2.0.4",
+ # punc_model_revision="master",
# spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
# spk_model_revision="v2.0.2",
)
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/demo.sh b/examples/industrial_data_pretraining/seaco_paraformer/demo.sh
index 9a02572..65847c7 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/demo.sh
+++ b/examples/industrial_data_pretraining/seaco_paraformer/demo.sh
@@ -1,10 +1,10 @@
model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
-vad_model_revision="v2.0.4"
+vad_model_revision="master"
punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
-punc_model_revision="v2.0.4"
+punc_model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/uniasr/demo.py b/examples/industrial_data_pretraining/uniasr/demo.py
index 3006d5e..0df06e2 100644
--- a/examples/industrial_data_pretraining/uniasr/demo.py
+++ b/examples/industrial_data_pretraining/uniasr/demo.py
@@ -6,7 +6,7 @@
from funasr import AutoModel
-model = AutoModel(model="iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline", model_revision="v2.0.4",)
+model = AutoModel(model="iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline", model_revision="master",)
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
@@ -16,7 +16,7 @@
''' can not use currently
from funasr import AutoFrontend
-frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.4")
+frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="master")
fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)
diff --git a/examples/industrial_data_pretraining/uniasr/demo.sh b/examples/industrial_data_pretraining/uniasr/demo.sh
index 71f249a..e38f974 100644
--- a/examples/industrial_data_pretraining/uniasr/demo.sh
+++ b/examples/industrial_data_pretraining/uniasr/demo.sh
@@ -1,6 +1,6 @@
model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
+model_revision="master"
python funasr/bin/inference.py \
+model=${model} \
diff --git a/examples/industrial_data_pretraining/whisper/infer.sh b/examples/industrial_data_pretraining/whisper/infer.sh
index 5beb7e2..6e8f247 100644
--- a/examples/industrial_data_pretraining/whisper/infer.sh
+++ b/examples/industrial_data_pretraining/whisper/infer.sh
@@ -11,7 +11,7 @@
output_dir="./outputs/debug"
model="iic/speech_whisper-large_asr_multilingual"
-model_revision="v2.0.4"
+model_revision="master"
device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index c31308e..73ddc19 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -109,7 +109,7 @@
if vad_model is not None:
logging.info("Building VAD model.")
vad_kwargs["model"] = vad_model
- vad_kwargs["model_revision"] = kwargs.get("vad_model_revision", None)
+ vad_kwargs["model_revision"] = kwargs.get("vad_model_revision", "master")
vad_kwargs["device"] = kwargs["device"]
vad_model, vad_kwargs = self.build_model(**vad_kwargs)
@@ -119,7 +119,7 @@
if punc_model is not None:
logging.info("Building punc model.")
punc_kwargs["model"] = punc_model
- punc_kwargs["model_revision"] = kwargs.get("punc_model_revision", None)
+ punc_kwargs["model_revision"] = kwargs.get("punc_model_revision", "master")
punc_kwargs["device"] = kwargs["device"]
punc_model, punc_kwargs = self.build_model(**punc_kwargs)
@@ -129,7 +129,7 @@
if spk_model is not None:
logging.info("Building SPK model.")
spk_kwargs["model"] = spk_model
- spk_kwargs["model_revision"] = kwargs.get("spk_model_revision", None)
+ spk_kwargs["model_revision"] = kwargs.get("spk_model_revision", "master")
spk_kwargs["device"] = kwargs["device"]
spk_model, spk_kwargs = self.build_model(**spk_kwargs)
self.cb_model = ClusterBackend().to(kwargs["device"])
diff --git a/funasr/download/download_from_hub.py b/funasr/download/download_from_hub.py
index 46704b0..75915f5 100644
--- a/funasr/download/download_from_hub.py
+++ b/funasr/download/download_from_hub.py
@@ -29,7 +29,7 @@
model_or_path = kwargs.get("model")
if model_or_path in name_maps_ms:
model_or_path = name_maps_ms[model_or_path]
- model_revision = kwargs.get("model_revision")
+ model_revision = kwargs.get("model_revision", "master")
if not os.path.exists(model_or_path) and "model_path" not in kwargs:
try:
model_or_path = get_or_download_model_dir(model_or_path, model_revision,
diff --git a/funasr/models/llm_asr/model.py b/funasr/models/llm_asr/model.py
index f5dd3b1..90cbd94 100644
--- a/funasr/models/llm_asr/model.py
+++ b/funasr/models/llm_asr/model.py
@@ -73,7 +73,7 @@
hub = audio_encoder_conf.get("hub", None)
if hub == "ms":
from funasr import AutoModel
- model = AutoModel(model=audio_encoder, model_revision="v2.0.4")
+ model = AutoModel(model=audio_encoder, model_revision="master")
# frontend = model.kwargs.get("frontend")
audio_encoder_output_size = model.model.encoder_output_size
diff --git a/funasr/models/llm_asr_nar/model.py b/funasr/models/llm_asr_nar/model.py
index 06b2193..30537cf 100644
--- a/funasr/models/llm_asr_nar/model.py
+++ b/funasr/models/llm_asr_nar/model.py
@@ -75,7 +75,7 @@
if hub == "funasr":
from funasr import AutoModel
init_param_path = encoder_conf.get("init_param_path", "iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
- model = AutoModel(model=init_param_path, model_revision="v2.0.4")
+ model = AutoModel(model=init_param_path, model_revision="master")
# frontend = model.kwargs.get("frontend")
model.model.decoder = None
@@ -406,7 +406,7 @@
from funasr import AutoModel
init_param_path = encoder_conf.get("init_param_path",
"iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
- model = AutoModel(model=init_param_path, model_revision="v2.0.4")
+ model = AutoModel(model=init_param_path, model_revision="master")
# frontend = model.kwargs.get("frontend")
model.model.decoder = None
--
Gitblit v1.9.1