seamless_communication-main.zip
大小:13.65MB
价格:25积分
下载量:0
评分:
5.0
上传者:weixin_43620082
更新日期:2025-09-22

自动语音翻译 seamless

资源文件列表(大概)

文件名
大小
seamless_communication-main/
-
seamless_communication-main/.gitignore
1.82KB
seamless_communication-main/.gitmodules
84B
seamless_communication-main/.pre-commit-config.yaml
360B
seamless_communication-main/23-11_SEAMLESS_BlogHero_11.17.jpg
287.93KB
seamless_communication-main/ACCEPTABLE_USE_POLICY
4.84KB
seamless_communication-main/CODE_OF_CONDUCT.md
3.45KB
seamless_communication-main/CONTRIBUTING.md
1.49KB
seamless_communication-main/LICENSE
18.88KB
seamless_communication-main/MIT_LICENSE
1.06KB
seamless_communication-main/README.md
22.85KB
seamless_communication-main/SEAMLESS_LICENSE
9.8KB
seamless_communication-main/Seamless_Tutorial.ipynb
8.47MB
seamless_communication-main/demo/
-
seamless_communication-main/demo/.gitignore
7B
seamless_communication-main/demo/dino_pretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/dinopretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/dinopretssel/clean_spk1_default_00240_pred.wav
211.92KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/dinopretssel/clean_spk2_default_00026_pred.wav
180.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/dinopretssel/noisy_spk1_default_00240_pred.wav
174.42KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/dinopretssel/noisy_spk2_default_00026_pred.wav
126.61KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel+denoiser/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel+denoiser/clean_spk1_default_00240_pred.wav
211.92KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel+denoiser/clean_spk2_default_00026_pred.wav
180.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel+denoiser/noisy_spk1_default_00240_pred.wav
174.42KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel+denoiser/noisy_spk2_default_00026_pred.wav
126.61KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel/clean_spk1_default_00240_pred.wav
211.92KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel/clean_spk2_default_00026_pred.wav
180.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel/noisy_spk1_default_00240_pred.wav
174.42KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/pretssel/noisy_spk2_default_00026_pred.wav
126.61KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/ref/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/ref/clean_spk1_default_00240.wav
119.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/ref/clean_spk2_default_00026.wav
97.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/ref/noisy_spk1_default_00240.wav
174KB
seamless_communication-main/demo/dino_pretssel/audios/employee_eng_spa/ref/noisy_spk2_default_00026.wav
105.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/dinopretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/dinopretssel/clean_spk3_00032_pred.wav
134.11KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/dinopretssel/clean_spk4_00003_pred.wav
170.67KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/dinopretssel/noisy_spk3_00032_pred.wav
148.17KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/dinopretssel/noisy_spk4_00003_pred.wav
183.79KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel+denoiser/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel+denoiser/clean_spk3_00032_pred.wav
134.11KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel+denoiser/clean_spk4_00003_pred.wav
170.67KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel+denoiser/noisy_spk3_00032_pred.wav
148.17KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel+denoiser/noisy_spk4_00003_pred.wav
183.79KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel/clean_spk3_00032_pred.wav
134.11KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel/clean_spk4_00003_pred.wav
170.67KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel/noisy_spk3_00032_pred.wav
148.17KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/pretssel/noisy_spk4_00003_pred.wav
183.79KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/ref/
-
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/ref/clean_spk3_00032.wav
124.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/ref/clean_spk4_00003.wav
109.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/ref/noisy_spk3_00032.wav
177.04KB
seamless_communication-main/demo/dino_pretssel/audios/employee_spa_eng/ref/noisy_spk4_00003.wav
130.04KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/dinopretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/dinopretssel/005_#4.wav
88.17KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/dinopretssel/022_#41.wav
42.23KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/pretssel+denoiser/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/pretssel+denoiser/005_#4.wav
88.17KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/pretssel+denoiser/022_#41.wav
42.23KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/pretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/pretssel/005_#4.wav
88.17KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/pretssel/022_#41.wav
42.23KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/ref/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/ref/005_#4.wav
67.54KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/clean/ref/022_#41.wav
41.92KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/dinopretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/dinopretssel/005_#4.wav
72.23KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/dinopretssel/022_#41.wav
50.67KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/pretssel+denoiser/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/pretssel+denoiser/005_#4.wav
72.23KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/pretssel+denoiser/022_#41.wav
50.67KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/pretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/pretssel/005_#4.wav
72.23KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/pretssel/022_#41.wav
50.67KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/ref/
-
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/ref/005_#4.wav
67.54KB
seamless_communication-main/demo/dino_pretssel/audios/mdral_spa_eng/noisy/ref/022_#41.wav
41.92KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/dinopretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/dinopretssel/s07_default_00066.wav
122.86KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/dinopretssel/s08_default_00020.wav
134.11KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/pretssel+denoiser/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/pretssel+denoiser/s07_default_00066.wav
122.86KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/pretssel+denoiser/s08_default_00020.wav
134.11KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/pretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/pretssel/s07_default_00066.wav
122.86KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/pretssel/s08_default_00020.wav
134.11KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/ref/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/ref/s07_default_00066.wav
65.87KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/clean/ref/s08_default_00020.wav
79.25KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/dinopretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/dinopretssel/s07_default_00066.wav
91.92KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/dinopretssel/s08_default_00020.wav
103.17KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/pretssel+denoiser/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/pretssel+denoiser/s07_default_00066.wav
91.92KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/pretssel+denoiser/s08_default_00020.wav
103.17KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/pretssel/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/pretssel/s07_default_00066.wav
91.92KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/pretssel/s08_default_00020.wav
103.17KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/ref/
-
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/ref/s07_default_00066.wav
65.87KB
seamless_communication-main/demo/dino_pretssel/audios/mexpresso_eng_spa/noisy/ref/s08_default_00020.wav
79.25KB
seamless_communication-main/demo/dino_pretssel/index.html
52.92KB
seamless_communication-main/demo/dino_pretssel/jquery-3.5.js
87.39KB
seamless_communication-main/demo/dino_pretssel/styles.css
7.14KB
seamless_communication-main/demo/dino_pretssel/wavesurfer.js
194.73KB
seamless_communication-main/demo/expressive/
-
seamless_communication-main/demo/expressive/app.py
8.87KB
seamless_communication-main/demo/expressive/requirements.txt
78B
seamless_communication-main/demo/expressive/utils.py
2.35KB
seamless_communication-main/demo/m4tv1/
-
seamless_communication-main/demo/m4tv1/app.py
19.13KB
seamless_communication-main/demo/m4tv1/requirements.txt
112B
seamless_communication-main/demo/m4tv2/
-
seamless_communication-main/demo/m4tv2/app.py
12KB
seamless_communication-main/demo/m4tv2/lang_list.py
4.47KB
seamless_communication-main/demo/m4tv2/requirements.txt
78B
seamless_communication-main/dev_requirements.txt
53B
seamless_communication-main/docs/
-
seamless_communication-main/docs/expressive/
-
seamless_communication-main/docs/expressive/README.md
9.68KB
seamless_communication-main/docs/expressive/seamless_align_expressive_README.md
2.18KB
seamless_communication-main/docs/expressive/seamlessexpressive_arch.jpg
179.33KB
seamless_communication-main/docs/m4t/
-
seamless_communication-main/docs/m4t/README.md
20.43KB
seamless_communication-main/docs/m4t/en_alignment.png
137.85KB
seamless_communication-main/docs/m4t/on_device_README.md
3.11KB
seamless_communication-main/docs/m4t/ru_alignment.png
119.61KB
seamless_communication-main/docs/m4t/seamless_align_README.md
32.92KB
seamless_communication-main/docs/m4t/seamlessm4t_arch.svg
48.9KB
seamless_communication-main/docs/m4t/unity2_aligner_README.md
3.3KB
seamless_communication-main/docs/streaming/
-
seamless_communication-main/docs/streaming/README.md
3.36KB
seamless_communication-main/docs/streaming/streaming_arch.png
166.3KB
seamless_communication-main/ggml/
-
seamless_communication-main/ggml/CMakeLists.txt
6.69KB
seamless_communication-main/ggml/LICENSE
1.05KB
seamless_communication-main/ggml/Makefile
1.34KB
seamless_communication-main/ggml/README.md
2.93KB
seamless_communication-main/ggml/build.zig
4.65KB
seamless_communication-main/ggml/ci/
-
seamless_communication-main/ggml/ci/run.sh
6.1KB
seamless_communication-main/ggml/cmake/
-
seamless_communication-main/ggml/cmake/BuildTypes.cmake
1.99KB
seamless_communication-main/ggml/cmake/GitVars.cmake
717B
seamless_communication-main/ggml/ctypes_utils.py
2.61KB
seamless_communication-main/ggml/examples/
-
seamless_communication-main/ggml/examples/CMakeLists.txt
612B
seamless_communication-main/ggml/examples/common-ggml.cpp
8.47KB
seamless_communication-main/ggml/examples/common-ggml.h
410B
seamless_communication-main/ggml/examples/common.cpp
27.06KB
seamless_communication-main/ggml/examples/common.h
5.17KB
seamless_communication-main/ggml/examples/dr_wav.h
235.7KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/
-
seamless_communication-main/ggml/examples/kaldi-native-fbank/CMakeLists.txt
182B
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/
-
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/CMakeLists.txt
2.05KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/feature-fbank.cc
3.86KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/feature-fbank.h
4.39KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/feature-functions.cc
1.54KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/feature-functions.h
1.5KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/feature-window.cc
7.92KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/feature-window.h
6.67KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/fftsg.c
78.35KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/log.cc
4.38KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/log.h
11.02KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/mel-computations.cc
9.42KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/mel-computations.h
3.89KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/online-feature.cc
5.26KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/online-feature.h
5.27KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/rfft.cc
1.68KB
seamless_communication-main/ggml/examples/kaldi-native-fbank/csrc/rfft.h
1.56KB
seamless_communication-main/ggml/examples/python/
-
seamless_communication-main/ggml/examples/python/README.md
4.71KB
seamless_communication-main/ggml/examples/python/api.h
411B
seamless_communication-main/ggml/examples/python/example_add_quant.py
853B
seamless_communication-main/ggml/examples/python/example_test_all_quants.py
1.9KB
seamless_communication-main/ggml/examples/python/ggml/
-
seamless_communication-main/ggml/examples/python/ggml/__init__.py
1.87KB
seamless_communication-main/ggml/examples/python/ggml/__init__.pyi
93.12KB
seamless_communication-main/ggml/examples/python/ggml/cffi.py
50.37KB
seamless_communication-main/ggml/examples/python/ggml/ffi/
-
seamless_communication-main/ggml/examples/python/ggml/ffi/__init__.pyi
60B
seamless_communication-main/ggml/examples/python/ggml/utils.py
8.75KB
seamless_communication-main/ggml/examples/python/regenerate.py
2.09KB
seamless_communication-main/ggml/examples/python/stubs.py
4.41KB
seamless_communication-main/ggml/examples/python/test_tensor.py
9.28KB
seamless_communication-main/ggml/examples/unity/
-
seamless_communication-main/ggml/examples/unity/CMakeLists.txt
948B
seamless_communication-main/ggml/examples/unity/fairseq2.cpp
69.8KB
seamless_communication-main/ggml/examples/unity/fairseq2.h
9.78KB
seamless_communication-main/ggml/examples/unity/lib/
-
seamless_communication-main/ggml/examples/unity/lib/unity_lib.cpp
7.9KB
seamless_communication-main/ggml/examples/unity/lib/unity_lib.h
1.29KB
seamless_communication-main/ggml/examples/unity/model_loader.cpp
7.81KB
seamless_communication-main/ggml/examples/unity/model_loader.h
912B
seamless_communication-main/ggml/examples/unity/unity.cpp
7.81KB
seamless_communication-main/ggml/ggml.pc.in
241B
seamless_communication-main/ggml/ggml.py
15.78KB
seamless_communication-main/ggml/ggml_convert.py
25.16KB
seamless_communication-main/ggml/include/
-
seamless_communication-main/ggml/include/ggml/
-
seamless_communication-main/ggml/include/ggml/ggml-alloc.h
3.76KB
seamless_communication-main/ggml/include/ggml/ggml-backend.h
8.4KB
seamless_communication-main/ggml/include/ggml/ggml.h
80.77KB
seamless_communication-main/ggml/mt.py
7.18KB
seamless_communication-main/ggml/requirements.txt
157B
seamless_communication-main/ggml/scripts/
-
seamless_communication-main/ggml/scripts/sync-llama.sh
929B
seamless_communication-main/ggml/scripts/sync-whisper.sh
1.26KB
seamless_communication-main/ggml/src/
-
seamless_communication-main/ggml/src/CMakeLists.txt
13.81KB
seamless_communication-main/ggml/src/ggml-alloc.c
27.75KB
seamless_communication-main/ggml/src/ggml-backend-impl.h
4.49KB
seamless_communication-main/ggml/src/ggml-backend.c
48.81KB
seamless_communication-main/ggml/src/ggml-cuda.cu
250.53KB
seamless_communication-main/ggml/src/ggml-cuda.h
1.68KB
seamless_communication-main/ggml/src/ggml-impl.h
7.21KB
seamless_communication-main/ggml/src/ggml-metal.h
3.34KB
seamless_communication-main/ggml/src/ggml-metal.m
60.64KB
seamless_communication-main/ggml/src/ggml-metal.metal
76.46KB
seamless_communication-main/ggml/src/ggml-opencl.cpp
67.24KB
seamless_communication-main/ggml/src/ggml-opencl.h
845B
seamless_communication-main/ggml/src/ggml-quants.c
284.4KB
seamless_communication-main/ggml/src/ggml-quants.h
9.99KB
seamless_communication-main/ggml/src/ggml.c
624.27KB
seamless_communication-main/ggml/test_ggml_integration.py
13.41KB
seamless_communication-main/ggml/test_unity_cpp.py
25.83KB
seamless_communication-main/ggml/tests/
-
seamless_communication-main/ggml/tests/CMakeLists.txt
12.8KB
seamless_communication-main/ggml/tests/test-blas0.c
6.48KB
seamless_communication-main/ggml/tests/test-conv-transpose.c
5.84KB
seamless_communication-main/ggml/tests/test-customop.c
6.55KB
seamless_communication-main/ggml/tests/test-grad0.cpp
51.62KB
seamless_communication-main/ggml/tests/test-mul-mat0.c
10.53KB
seamless_communication-main/ggml/tests/test-mul-mat1.c
8.79KB
seamless_communication-main/ggml/tests/test-mul-mat2.c
89.62KB
seamless_communication-main/ggml/tests/test-opt.cpp
5.6KB
seamless_communication-main/ggml/tests/test-pool.c
4.33KB
seamless_communication-main/ggml/tests/test-quantize-fns.cpp
5.48KB
seamless_communication-main/ggml/tests/test-quantize-perf.cpp
13.68KB
seamless_communication-main/ggml/tests/test-rel-pos.c
2.96KB
seamless_communication-main/ggml/tests/test-svd0.c
5.02KB
seamless_communication-main/ggml/tests/test-vec0.c
3.32KB
seamless_communication-main/ggml/tests/test-vec1.c
20.69KB
seamless_communication-main/ggml/tests/test-vec2.c
7.14KB
seamless_communication-main/ggml/tests/test-xpos.c
3.02KB
seamless_communication-main/ggml/tests/test0.c
1.21KB
seamless_communication-main/ggml/tests/test0.zig
1.39KB
seamless_communication-main/ggml/tests/test1.c
15.23KB
seamless_communication-main/ggml/tests/test1.zig
17.64KB
seamless_communication-main/ggml/tests/test2.c
5.79KB
seamless_communication-main/ggml/tests/test2.zig
5.69KB
seamless_communication-main/ggml/tests/test3.c
2.78KB
seamless_communication-main/ggml/tests/test3.zig
3.2KB
seamless_communication-main/ggml/third_party_ggml.py
269.14KB
seamless_communication-main/pyproject.toml
982B
seamless_communication-main/seamlessM4T.png
193.88KB
seamless_communication-main/setup.py
1.9KB
seamless_communication-main/src/
-
seamless_communication-main/src/seamless_communication/
-
seamless_communication-main/src/seamless_communication/__init__.py
516B
seamless_communication-main/src/seamless_communication/cards/
-
seamless_communication-main/src/seamless_communication/cards/conformer_shaw.yaml
368B
seamless_communication-main/src/seamless_communication/cards/expresso.yaml
294B
seamless_communication-main/src/seamless_communication/cards/mexpresso_text.yaml
312B
seamless_communication-main/src/seamless_communication/cards/mintox.yaml
819B
seamless_communication-main/src/seamless_communication/cards/mutox.yaml
355B
seamless_communication-main/src/seamless_communication/cards/nano.yaml
872B
seamless_communication-main/src/seamless_communication/cards/nar_t2u_aligner.yaml
809B
seamless_communication-main/src/seamless_communication/cards/seamlessM4T_large.yaml
711B
seamless_communication-main/src/seamless_communication/cards/seamlessM4T_medium.yaml
716B
seamless_communication-main/src/seamless_communication/cards/seamlessM4T_v2_large.yaml
829B
seamless_communication-main/src/seamless_communication/cards/seamless_expressivity.yaml
814B
seamless_communication-main/src/seamless_communication/cards/seamless_streaming_monotonic_decoder.yaml
414B
seamless_communication-main/src/seamless_communication/cards/seamless_streaming_unity.yaml
820B
seamless_communication-main/src/seamless_communication/cards/unity_nllb-100.yaml
1.13KB
seamless_communication-main/src/seamless_communication/cards/unity_nllb-200.yaml
1.97KB
seamless_communication-main/src/seamless_communication/cards/vocoder_36langs.yaml
3.92KB
seamless_communication-main/src/seamless_communication/cards/vocoder_pretssel.yaml
4.62KB
seamless_communication-main/src/seamless_communication/cards/vocoder_pretssel_16khz.yaml
4.62KB
seamless_communication-main/src/seamless_communication/cards/vocoder_v2.yaml
3.22KB
seamless_communication-main/src/seamless_communication/cards/xlsr2_1b_v2.yaml
371B
seamless_communication-main/src/seamless_communication/cli/
-
seamless_communication-main/src/seamless_communication/cli/__init__.py
201B
seamless_communication-main/src/seamless_communication/cli/eval_utils/
-
seamless_communication-main/src/seamless_communication/cli/eval_utils/__init__.py
633B
seamless_communication-main/src/seamless_communication/cli/eval_utils/compute_metrics.py
13.86KB
seamless_communication-main/src/seamless_communication/cli/eval_utils/lang_mapping.py
3.11KB
seamless_communication-main/src/seamless_communication/cli/expressivity/
-
seamless_communication-main/src/seamless_communication/cli/expressivity/__init__.py
201B
seamless_communication-main/src/seamless_communication/cli/expressivity/data/
-
seamless_communication-main/src/seamless_communication/cli/expressivity/data/__init__.py
201B
seamless_communication-main/src/seamless_communication/cli/expressivity/data/prepare_mexpresso.py
7.78KB
seamless_communication-main/src/seamless_communication/cli/expressivity/evaluate/
-
seamless_communication-main/src/seamless_communication/cli/expressivity/evaluate/__init__.py
-
seamless_communication-main/src/seamless_communication/cli/expressivity/evaluate/evaluate.py
10.13KB
seamless_communication-main/src/seamless_communication/cli/expressivity/evaluate/post_process_pauserate.py
1.53KB
seamless_communication-main/src/seamless_communication/cli/expressivity/evaluate/run_asr_bleu.py
884B
seamless_communication-main/src/seamless_communication/cli/expressivity/predict/
-
seamless_communication-main/src/seamless_communication/cli/expressivity/predict/__init__.py
201B
seamless_communication-main/src/seamless_communication/cli/expressivity/predict/predict.py
5.01KB
seamless_communication-main/src/seamless_communication/cli/expressivity/predict/pretssel_generator.py
3KB
seamless_communication-main/src/seamless_communication/cli/m4t/
-
seamless_communication-main/src/seamless_communication/cli/m4t/__init__.py
-
seamless_communication-main/src/seamless_communication/cli/m4t/audio_to_units/
-
seamless_communication-main/src/seamless_communication/cli/m4t/audio_to_units/README.md
1.06KB
seamless_communication-main/src/seamless_communication/cli/m4t/audio_to_units/__init__.py
202B
seamless_communication-main/src/seamless_communication/cli/m4t/audio_to_units/audio_to_units.py
1.65KB
seamless_communication-main/src/seamless_communication/cli/m4t/evaluate/
-
seamless_communication-main/src/seamless_communication/cli/m4t/evaluate/README.md
1.03KB
seamless_communication-main/src/seamless_communication/cli/m4t/evaluate/__init__.py
202B
seamless_communication-main/src/seamless_communication/cli/m4t/evaluate/evaluate.py
17.6KB
seamless_communication-main/src/seamless_communication/cli/m4t/finetune/
-
seamless_communication-main/src/seamless_communication/cli/m4t/finetune/README.md
7.29KB
seamless_communication-main/src/seamless_communication/cli/m4t/finetune/__init__.py
202B
seamless_communication-main/src/seamless_communication/cli/m4t/finetune/dataloader.py
11.09KB
seamless_communication-main/src/seamless_communication/cli/m4t/finetune/dataset.py
7.53KB
seamless_communication-main/src/seamless_communication/cli/m4t/finetune/dist_utils.py
1.89KB
seamless_communication-main/src/seamless_communication/cli/m4t/finetune/finetune.py
6.48KB
seamless_communication-main/src/seamless_communication/cli/m4t/finetune/trainer.py
16.47KB
seamless_communication-main/src/seamless_communication/cli/m4t/predict/
-
seamless_communication-main/src/seamless_communication/cli/m4t/predict/README.md
3.67KB
seamless_communication-main/src/seamless_communication/cli/m4t/predict/__init__.py
433B
seamless_communication-main/src/seamless_communication/cli/m4t/predict/predict.py
7.59KB
seamless_communication-main/src/seamless_communication/cli/streaming/
-
seamless_communication-main/src/seamless_communication/cli/streaming/README.md
3.01KB
seamless_communication-main/src/seamless_communication/cli/streaming/__init__.py
201B
seamless_communication-main/src/seamless_communication/cli/streaming/evaluate.py
3.18KB
seamless_communication-main/src/seamless_communication/cli/streaming/scorers/
-
seamless_communication-main/src/seamless_communication/cli/streaming/scorers/__init__.py
201B
seamless_communication-main/src/seamless_communication/cli/streaming/scorers/seamless_quality_scorer.py
4.76KB
seamless_communication-main/src/seamless_communication/cli/toxicity/
-
seamless_communication-main/src/seamless_communication/cli/toxicity/etox/
-
seamless_communication-main/src/seamless_communication/cli/toxicity/etox/README.md
3.88KB
seamless_communication-main/src/seamless_communication/cli/toxicity/etox/asr_etox.py
7.07KB
seamless_communication-main/src/seamless_communication/cli/toxicity/etox/etox.py
1.24KB
seamless_communication-main/src/seamless_communication/cli/toxicity/mutox/
-
seamless_communication-main/src/seamless_communication/cli/toxicity/mutox/README.md
4.12KB
seamless_communication-main/src/seamless_communication/cli/toxicity/mutox/mutox_example.ipynb
6.13KB
seamless_communication-main/src/seamless_communication/cli/toxicity/mutox/mutox_speech.py
3.72KB
seamless_communication-main/src/seamless_communication/cli/toxicity/mutox/mutox_text.py
2.58KB
seamless_communication-main/src/seamless_communication/cli/toxicity/mutox_group_annotations/
-
seamless_communication-main/src/seamless_communication/cli/toxicity/mutox_group_annotations/README.md
3.14KB
seamless_communication-main/src/seamless_communication/datasets/
-
seamless_communication-main/src/seamless_communication/datasets/__init__.py
201B
seamless_communication-main/src/seamless_communication/datasets/datatypes.py
1.22KB
seamless_communication-main/src/seamless_communication/datasets/huggingface.py
8.2KB
seamless_communication-main/src/seamless_communication/denoise/
-
seamless_communication-main/src/seamless_communication/denoise/__init__.py
-
seamless_communication-main/src/seamless_communication/denoise/demucs.py
4.03KB
seamless_communication-main/src/seamless_communication/inference/
-
seamless_communication-main/src/seamless_communication/inference/README.md
3.57KB
seamless_communication-main/src/seamless_communication/inference/__init__.py
828B
seamless_communication-main/src/seamless_communication/inference/generator.py
13.34KB
seamless_communication-main/src/seamless_communication/inference/transcriber.py
13.89KB
seamless_communication-main/src/seamless_communication/inference/translator.py
15.29KB
seamless_communication-main/src/seamless_communication/models/
-
seamless_communication-main/src/seamless_communication/models/__init__.py
201B
seamless_communication-main/src/seamless_communication/models/aligner/
-
seamless_communication-main/src/seamless_communication/models/aligner/__init__.py
542B
seamless_communication-main/src/seamless_communication/models/aligner/alignment_extractor.py
6.01KB
seamless_communication-main/src/seamless_communication/models/aligner/builder.py
5.3KB
seamless_communication-main/src/seamless_communication/models/aligner/loader.py
2.85KB
seamless_communication-main/src/seamless_communication/models/aligner/model.py
10.03KB
seamless_communication-main/src/seamless_communication/models/conformer_shaw/
-
seamless_communication-main/src/seamless_communication/models/conformer_shaw/__init__.py
847B
seamless_communication-main/src/seamless_communication/models/conformer_shaw/builder.py
5.69KB
seamless_communication-main/src/seamless_communication/models/conformer_shaw/loader.py
4.29KB
seamless_communication-main/src/seamless_communication/models/generator/
-
seamless_communication-main/src/seamless_communication/models/generator/__init__.py
202B
seamless_communication-main/src/seamless_communication/models/generator/builder.py
15.72KB
seamless_communication-main/src/seamless_communication/models/generator/ecapa_tdnn.py
13.62KB
seamless_communication-main/src/seamless_communication/models/generator/ecapa_tdnn_builder.py
2.88KB
seamless_communication-main/src/seamless_communication/models/generator/loader.py
858B
seamless_communication-main/src/seamless_communication/models/generator/streamable.py
15.48KB
seamless_communication-main/src/seamless_communication/models/generator/vocoder.py
19.9KB
seamless_communication-main/src/seamless_communication/models/monotonic_decoder/
-
seamless_communication-main/src/seamless_communication/models/monotonic_decoder/__init__.py
1.1KB
seamless_communication-main/src/seamless_communication/models/monotonic_decoder/builder.py
7.91KB
seamless_communication-main/src/seamless_communication/models/monotonic_decoder/loader.py
4.15KB
seamless_communication-main/src/seamless_communication/models/monotonic_decoder/model.py
1.99KB
seamless_communication-main/src/seamless_communication/models/monotonic_decoder/monotonic_decoder.py
2.76KB
seamless_communication-main/src/seamless_communication/models/monotonic_decoder/monotonic_decoder_layer.py
5.72KB
seamless_communication-main/src/seamless_communication/models/monotonic_decoder/p_choose.py
4.17KB
seamless_communication-main/src/seamless_communication/models/pretssel/
-
seamless_communication-main/src/seamless_communication/models/pretssel/__init__.py
636B
seamless_communication-main/src/seamless_communication/models/pretssel/ecapa_tdnn.py
13.68KB
seamless_communication-main/src/seamless_communication/models/pretssel/ecapa_tdnn_builder.py
2.88KB
seamless_communication-main/src/seamless_communication/models/tokenizer.py
3.85KB
seamless_communication-main/src/seamless_communication/models/unit_extractor/
-
seamless_communication-main/src/seamless_communication/models/unit_extractor/__init__.py
556B
seamless_communication-main/src/seamless_communication/models/unit_extractor/kmeans.py
1.05KB
seamless_communication-main/src/seamless_communication/models/unit_extractor/unit_extractor.py
3.89KB
seamless_communication-main/src/seamless_communication/models/unit_extractor/wav2vec2_layer_output.py
3.36KB
seamless_communication-main/src/seamless_communication/models/unity/
-
seamless_communication-main/src/seamless_communication/models/unity/__init__.py
3.6KB
seamless_communication-main/src/seamless_communication/models/unity/adaptor_block.py
12.43KB
seamless_communication-main/src/seamless_communication/models/unity/builder.py
20.86KB
seamless_communication-main/src/seamless_communication/models/unity/char_tokenizer.py
3.16KB
seamless_communication-main/src/seamless_communication/models/unity/fft_decoder.py
2.4KB
seamless_communication-main/src/seamless_communication/models/unity/fft_decoder_layer.py
6.33KB
seamless_communication-main/src/seamless_communication/models/unity/film.py
1.71KB
seamless_communication-main/src/seamless_communication/models/unity/length_regulator.py
10.58KB
seamless_communication-main/src/seamless_communication/models/unity/loader.py
26.44KB
seamless_communication-main/src/seamless_communication/models/unity/model.py
15.38KB
seamless_communication-main/src/seamless_communication/models/unity/nar_decoder_frontend.py
11.55KB
seamless_communication-main/src/seamless_communication/models/unity/t2u_builder.py
22.06KB
seamless_communication-main/src/seamless_communication/models/unity/unit_tokenizer.py
7.73KB
seamless_communication-main/src/seamless_communication/models/vocoder/
-
seamless_communication-main/src/seamless_communication/models/vocoder/__init__.py
759B
seamless_communication-main/src/seamless_communication/models/vocoder/builder.py
3.98KB
seamless_communication-main/src/seamless_communication/models/vocoder/codehifigan.py
3.71KB
seamless_communication-main/src/seamless_communication/models/vocoder/hifigan.py
6.38KB
seamless_communication-main/src/seamless_communication/models/vocoder/loader.py
1.37KB
seamless_communication-main/src/seamless_communication/models/vocoder/vocoder.py
1.82KB
seamless_communication-main/src/seamless_communication/py.typed
-
seamless_communication-main/src/seamless_communication/segment/
-
seamless_communication-main/src/seamless_communication/segment/__init__.py
-
seamless_communication-main/src/seamless_communication/segment/silero_vad.py
9.77KB
seamless_communication-main/src/seamless_communication/store.py
1007B
seamless_communication-main/src/seamless_communication/streaming/
-
seamless_communication-main/src/seamless_communication/streaming/__init__.py
201B
seamless_communication-main/src/seamless_communication/streaming/agents/
-
seamless_communication-main/src/seamless_communication/streaming/agents/__init__.py
202B
seamless_communication-main/src/seamless_communication/streaming/agents/common.py
989B
seamless_communication-main/src/seamless_communication/streaming/agents/detokenizer.py
2.71KB
seamless_communication-main/src/seamless_communication/streaming/agents/dual_vocoder_agent.py
4KB
seamless_communication-main/src/seamless_communication/streaming/agents/offline_w2v_bert_encoder.py
3.72KB
seamless_communication-main/src/seamless_communication/streaming/agents/online_feature_extractor.py
4.83KB
seamless_communication-main/src/seamless_communication/streaming/agents/online_text_decoder.py
15.01KB
seamless_communication-main/src/seamless_communication/streaming/agents/online_unit_decoder.py
5.73KB
seamless_communication-main/src/seamless_communication/streaming/agents/online_vocoder.py
2.73KB
seamless_communication-main/src/seamless_communication/streaming/agents/pretssel_vocoder.py
5.55KB
seamless_communication-main/src/seamless_communication/streaming/agents/seamless_s2st.py
2.29KB
seamless_communication-main/src/seamless_communication/streaming/agents/seamless_streaming_s2st.py
1.96KB
seamless_communication-main/src/seamless_communication/streaming/agents/seamless_streaming_s2t.py
1.41KB
seamless_communication-main/src/seamless_communication/streaming/agents/silero_vad.py
12.96KB
seamless_communication-main/src/seamless_communication/streaming/agents/unity_pipeline.py
8.1KB
seamless_communication-main/src/seamless_communication/streaming/dataloaders/
-
seamless_communication-main/src/seamless_communication/streaming/dataloaders/__init__.py
340B
seamless_communication-main/src/seamless_communication/streaming/dataloaders/s2tt.py
8.31KB
seamless_communication-main/src/seamless_communication/toxicity/
-
seamless_communication-main/src/seamless_communication/toxicity/__init__.py
450B
seamless_communication-main/src/seamless_communication/toxicity/etox_bad_word_checker.py
5.86KB
seamless_communication-main/src/seamless_communication/toxicity/mintox.py
7.77KB
seamless_communication-main/src/seamless_communication/toxicity/mutox/
-
seamless_communication-main/src/seamless_communication/toxicity/mutox/builder.py
2.16KB
seamless_communication-main/src/seamless_communication/toxicity/mutox/classifier.py
914B
seamless_communication-main/src/seamless_communication/toxicity/mutox/loader.py
1.17KB
seamless_communication-main/src/seamless_communication/toxicity/mutox/speech_pipeline.py
2.03KB
seamless_communication-main/tests/
-
seamless_communication-main/tests/__init__.py
264B
seamless_communication-main/tests/common.py
3.27KB
seamless_communication-main/tests/conftest.py
1.5KB
seamless_communication-main/tests/integration/
-
seamless_communication-main/tests/integration/__init__.py
201B
seamless_communication-main/tests/integration/inference/
-
seamless_communication-main/tests/integration/inference/__init__.py
-
seamless_communication-main/tests/integration/inference/test_mintox.py
4.26KB
seamless_communication-main/tests/integration/inference/test_translator.py
3.5KB
seamless_communication-main/tests/integration/models/
-
seamless_communication-main/tests/integration/models/__init__.py
201B
seamless_communication-main/tests/integration/models/test_conformer_shaw.py
1.17KB
seamless_communication-main/tests/integration/models/test_unity2_aligner.py
2.72KB
seamless_communication-main/tests/unit/
-
seamless_communication-main/tests/unit/__init__.py
201B
seamless_communication-main/tests/unit/denoise/
-
seamless_communication-main/tests/unit/denoise/__init__.py
-
seamless_communication-main/tests/unit/denoise/test_demucs.py
1.55KB
seamless_communication-main/tests/unit/models/
-
seamless_communication-main/tests/unit/models/__init__.py
201B
seamless_communication-main/tests/unit/models/unity/
-
seamless_communication-main/tests/unit/models/unity/__init__.py
201B
seamless_communication-main/tests/unit/models/unity/test_unity.py
7.79KB
seamless_communication-main/tests/unit/segment/
-
seamless_communication-main/tests/unit/segment/__init__.py
-
seamless_communication-main/tests/unit/segment/test_silero_vad.py
1.9KB

资源内容介绍

seamless
![](23-11_SEAMLESS_BlogHero_11.17.jpg)# Seamless IntroSeamless is a family of AI models that enable more natural and authentic communication across languages. SeamlessM4T is a massive multilingual multimodal machine translation model supporting around 100 languages. SeamlessM4T serves as foundation for SeamlessExpressive, a model that preserves elements of prosody and voice style across languages and SeamlessStreaming, a model supporting simultaneous translation and streaming ASR for around 100 languages. SeamlessExpressive and SeamlessStreaming are combined into Seamless, a unified model featuring multilinguality, real-time and expressive translations.## Links### Demos| | SeamlessM4T v2 | SeamlessExpressive | SeamlessStreaming || ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------- || Demo | [SeamlessM4T v2 Demo](https://seamless.metademolab.com/m4t?utm_source=github&utm_medium=web&utm_campaign=seamless&utm_content=readme) | [SeamlessExpressive Demo](https://seamless.metademolab.com/expressive?utm_source=github&utm_medium=web&utm_campaign=seamless&utm_content=readme) | || HuggingFace Space Demo | [🤗 SeamlessM4T v2 Space](https://huggingface.co/spaces/facebook/seamless-m4t-v2-large) | [🤗 SeamlessExpressive Space](https://huggingface.co/spaces/facebook/seamless-expressive) | [🤗 SeamlessStreaming Space](https://huggingface.co/spaces/facebook/seamless-streaming) |### Papers[Seamless](https://ai.facebook.com/research/publications/seamless-multilingual-expressive-and-streaming-speech-translation/)[EMMA](https://ai.meta.com/research/publications/efficient-monotonic-multihead-attention/)[SONAR](https://ai.meta.com/research/publications/sonar-expressive-zero-shot-expressive-speech-to-speech-translation/)### Blog[AI at Meta Blog](https://ai.meta.com/research/seamless-communication/)## TutorialAn exhaustive [tutorial](Seamless_Tutorial.ipynb) given at the NeurIPS 2023 - Seamless EXPO, which is a one-stop shop to learn how to use the entire suite of Seamless models. Please feel free to play with the notebook.## SeamlessM4TSeamlessM4T is our foundational all-in-one **M**assively **M**ultilingual and **M**ultimodal **M**achine **T**ranslation model delivering high-quality translation for speech and text in nearly 100 languages.SeamlessM4T models support the tasks of:- Speech-to-speech translation (S2ST)- Speech-to-text translation (S2TT)- Text-to-speech translation (T2ST)- Text-to-text translation (T2TT)- Automatic speech recognition (ASR):star2: We are releasing SeamlessM4T v2, an updated version with our novel *UnitY2* architecture. This new model improves over SeamlessM4T v1 in quality as well as inference latency in speech generation tasks.To learn more about the collection of SeamlessM4T models, the approach used in each, their language coverage and their performance, visit the [SeamlessM4T README](docs/m4t/README.md) or [🤗 Model Card](https://huggingface.co/facebook/seamless-m4t-v2-large).> [!NOTE]> Seamless M4T is also available in the 🤗 Transformers library. Visit [this section](docs/m4t/README.md#transformers-usage) for more details.## SeamlessExpressiveSeamlessExpressive is a speech-to-speech translation model that captures certain underexplored aspects of prosody such as speech rate and pauses, while preserving the style of one's voice and high content translation quality.To learn more about SeamlessExpressive models, visit the [SeamlessExpressive README](docs/expressive/README.md) or [🤗 Model Card](https://huggingface.co/facebook/seamless-expressive)## SeamlessStreamingSeamlessStreaming is a streaming translation model. The model supports speech as input modality and speech/text as output modalities.The SeamlessStreaming model supports the following tasks:- Speech-to-speech translation (S2ST)- Speech-to-text translation (S2TT)- Automatic speech recognition (ASR)To learn more about SeamlessStreaming models, visit the [SeamlessStreaming README](docs/streaming/README.md) or [🤗 Model Card](https://huggingface.co/facebook/seamless-streaming)## SeamlessThe Seamless model is the unified model for expressive streaming speech-to-speech translations.## What's new- [12/18/2023] We are open-sourcing our Conformer-based [W2v-BERT 2.0 speech encoder](#w2v-bert-20-speech-encoder) as described in Section 3.2.1 of the [paper](https://arxiv.org/pdf/2312.05187.pdf), which is at the core of our Seamless models.- [12/14/2023] We are releasing the Seamless [tutorial](#tutorial) given at NeurIPS 2023.# Quick Start## Installation> [!NOTE]> One of the prerequisites is [fairseq2](https://github.com/facebookresearch/fairseq2) which has pre-built packages available only> for Linux x86-64 and Apple-silicon Mac computers. In addition it has a dependency on [libsndfile](https://github.com/libsndfile/libsndfile) which> might not be installed on your machine. If you experience any installation issues, please refer to its> [README](https://github.com/facebookresearch/fairseq2) for further instructions.```pip install .```> [!NOTE]> Transcribing inference audio for computing metric uses [Whisper](https://github.com/openai/whisper#setup), which is automatically installed. Whisper in turn requires the command-line tool [`ffmpeg`](https://ffmpeg.org/) to be installed on your system, which is available from most package managers.## Running inference### SeamlessM4T InferenceHere’s an example of using the CLI from the root directory to run inference.S2ST task:```bashm4t_predict <path_to_input_audio> --task s2st --tgt_lang <tgt_lang> --output_path <path_to_save_audio>```T2TT task:```bashm4t_predict <input_text> --task t2tt --tgt_lang <tgt_lang> --src_lang <src_lang>```Please refer to the [inference README](src/seamless_communication/cli/m4t/predict) for detailed instruction on how to run inference and the list of supported languages on the source, target sides for speech, text modalities.For running S2TT/ASR natively (without Python) using GGML, please refer to [the unity.cpp section](#unitycpp).### SeamlessExpressive Inference> [!NOTE]> Please check the [section](#seamlessexpressive-models) on how to download the model.Here’s an example of using the CLI from the root directory to run inference.```bashexpressivity_predict <path_to_input_audio> --tgt_lang <tgt_lang> --model_name seamless_expressivity --vocoder_name vocoder_pretssel --output_path <path_to_save_audio>```### SeamlessStreaming and Seamless Inference[Streaming Evaluation README](src/seamless_communication/cli/streaming) has detailed instructions for running evaluations for the SeamlessStreaming and Seamless models. The CLI has an `--no-scoring` option that can be used to skip the scoring part and just run inference.Please check the inference [README](src/seamless_communication/inference) for more details.## Running SeamlessStreaming DemoYou can duplicate the [SeamlessStreaming HF space](https://huggingface.co/spaces/facebook/seamless-streaming?duplicate=true) to run the streaming demo.You can also run the demo loca

用户评论 (0)

发表评论

captcha