diff --git a/audio/gen_html.py b/audio/gen_html.py index 0830d92..77e9504 100644 --- a/audio/gen_html.py +++ b/audio/gen_html.py @@ -5,7 +5,7 @@ sys.path.append(pdj) print(pdj) -speaker_info_file = "/Users/jia/Downloads/speaker-info.txt" +speaker_info_file = "/Users/jiahong/Downloads/speaker-info.txt" speaker_gender_dic = {} with open(speaker_info_file, 'r', encoding='utf-8') as f: i = 0 @@ -166,12 +166,68 @@ def gen_tb_html(vits_save_base_dir, vq_save_base_dir, source_wav_name, target_wa # target_wav_name = to_sp.split("_to_")[1] # process_data(source_wav_name, target_wav_name) -# target wavs in libritts +# # target wavs in libritts +# +# +# base_dir = "/Users/jia/Downloads" +# vits_save_base_dir = "audio/vits_vctk_vc_to_libritts" +# vq_save_base_dir = "audio/vqmivc_vctk_vc_to_libritts" +# +# +# def process_data(source_wav_name, target_wav_name): +# tq_html = gen_tb_html(vits_save_base_dir, vq_save_base_dir, source_wav_name, target_wav_name) +# print(tq_html) +# cmd = f"cp -rf {base_dir}/{vits_save_base_dir.split('/')[-1]}/{source_wav_name}_to_{target_wav_name} {pdj}/{vits_save_base_dir}/ && cp -rf {base_dir}/{vq_save_base_dir.split('/')[-1]}/{source_wav_name}_to_{target_wav_name} {pdj}/{vq_save_base_dir}/" +# os.system(cmd) +# +# +# to_sp = "p231_406_to_7127_75947_000082_000005" +# source_wav_name = to_sp.split("_to_")[0] +# target_wav_name = to_sp.split("_to_")[1] +# process_data(source_wav_name, target_wav_name) +# # -------------------------------------------------------------- +# to_sp = "p231_406_to_8555_284447_000039_000002" +# source_wav_name = to_sp.split("_to_")[0] +# target_wav_name = to_sp.split("_to_")[1] +# process_data(source_wav_name, target_wav_name) +# # -------------------------------------------------------------- +# to_sp = "p251_010_to_6829_68771_000042_000002" +# source_wav_name = to_sp.split("_to_")[0] +# target_wav_name = to_sp.split("_to_")[1] +# process_data(source_wav_name, target_wav_name) +# # -------------------------------------------------------------- +# to_sp = "p274_247_to_2830_3979_000021_000000" +# source_wav_name = to_sp.split("_to_")[0] +# target_wav_name = to_sp.split("_to_")[1] +# process_data(source_wav_name, target_wav_name) +# # -------------------------------------------------------------- +# to_sp = "p284_213_to_1995_1826_000031_000003_16k" +# source_wav_name = to_sp.split("_to_")[0] +# target_wav_name = to_sp.split("_to_")[1] +# process_data(source_wav_name, target_wav_name) +# # -------------------------------------------------------------- +# to_sp = "p293_287_to_121_127105_000041_000001" +# source_wav_name = to_sp.split("_to_")[0] +# target_wav_name = to_sp.split("_to_")[1] +# process_data(source_wav_name, target_wav_name) +# # -------------------------------------------------------------- +# to_sp = "p326_294_to_121_127105_000041_000001" +# source_wav_name = to_sp.split("_to_")[0] +# target_wav_name = to_sp.split("_to_")[1] +# process_data(source_wav_name, target_wav_name) +# # -------------------------------------------------------------- +# to_sp = "p334_210_to_237_126133_000011_000000_16k" +# source_wav_name = to_sp.split("_to_")[0] +# target_wav_name = to_sp.split("_to_")[1] +# process_data(source_wav_name, target_wav_name) +# # -------------------------------------------------------------- + +# 更高难度的 -base_dir = "/Users/jia/Downloads" -vits_save_base_dir = "audio/vits_vctk_vc_to_libritts" -vq_save_base_dir = "audio/vqmivc_vctk_vc_to_libritts" +base_dir = "/Users/jiahong/Documents/vcc/FlowCPCVC论文/提交做mos评分音频" +vits_save_base_dir = "audio/vits_yuqi" +vq_save_base_dir = "audio/vq_yuqi" def process_data(source_wav_name, target_wav_name): @@ -181,43 +237,27 @@ def process_data(source_wav_name, target_wav_name): os.system(cmd) -to_sp = "p231_406_to_7127_75947_000082_000005" +to_sp = "03-01-05-01-01-01-16_to_p334_018" source_wav_name = to_sp.split("_to_")[0] target_wav_name = to_sp.split("_to_")[1] process_data(source_wav_name, target_wav_name) # -------------------------------------------------------------- -to_sp = "p231_406_to_8555_284447_000039_000002" +to_sp = "0011_001750_to_20_205_000031_000000" source_wav_name = to_sp.split("_to_")[0] target_wav_name = to_sp.split("_to_")[1] process_data(source_wav_name, target_wav_name) # -------------------------------------------------------------- -to_sp = "p251_010_to_6829_68771_000042_000002" +to_sp = "男2_to_10011" source_wav_name = to_sp.split("_to_")[0] target_wav_name = to_sp.split("_to_")[1] process_data(source_wav_name, target_wav_name) # -------------------------------------------------------------- -to_sp = "p274_247_to_2830_3979_000021_000000" +to_sp = "EMD6_to_p231_012" source_wav_name = to_sp.split("_to_")[0] target_wav_name = to_sp.split("_to_")[1] process_data(source_wav_name, target_wav_name) # -------------------------------------------------------------- -to_sp = "p284_213_to_1995_1826_000031_000003_16k" +to_sp = "obm2_to_en-US-ElizabethNeural_1624631702559" source_wav_name = to_sp.split("_to_")[0] target_wav_name = to_sp.split("_to_")[1] -process_data(source_wav_name, target_wav_name) -# -------------------------------------------------------------- -to_sp = "p293_287_to_121_127105_000041_000001" -source_wav_name = to_sp.split("_to_")[0] -target_wav_name = to_sp.split("_to_")[1] -process_data(source_wav_name, target_wav_name) -# -------------------------------------------------------------- -to_sp = "p326_294_to_121_127105_000041_000001" -source_wav_name = to_sp.split("_to_")[0] -target_wav_name = to_sp.split("_to_")[1] -process_data(source_wav_name, target_wav_name) -# -------------------------------------------------------------- -to_sp = "p334_210_to_237_126133_000011_000000_16k" -source_wav_name = to_sp.split("_to_")[0] -target_wav_name = to_sp.split("_to_")[1] -process_data(source_wav_name, target_wav_name) -# -------------------------------------------------------------- +process_data(source_wav_name, target_wav_name) \ No newline at end of file diff --git a/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/0011_001750.wav b/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/0011_001750.wav new file mode 100644 index 0000000..164f18b Binary files /dev/null and b/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/0011_001750.wav differ diff --git a/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/0011_001750_to_20_205_000031_000000.wav b/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/0011_001750_to_20_205_000031_000000.wav new file mode 100644 index 0000000..0653545 Binary files /dev/null and b/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/0011_001750_to_20_205_000031_000000.wav differ diff --git a/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/20_205_000031_000000.wav b/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/20_205_000031_000000.wav new file mode 100644 index 0000000..8cd16d1 Binary files /dev/null and b/audio/vits_yuqi/0011_001750_to_20_205_000031_000000/20_205_000031_000000.wav differ diff --git a/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16.wav b/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16.wav new file mode 100644 index 0000000..4361ab6 Binary files /dev/null and b/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16.wav differ diff --git a/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16_to_p334_018.wav b/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16_to_p334_018.wav new file mode 100644 index 0000000..79faa96 Binary files /dev/null and b/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16_to_p334_018.wav differ diff --git a/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/p334_018.wav b/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/p334_018.wav new file mode 100644 index 0000000..b29fdfb Binary files /dev/null and b/audio/vits_yuqi/03-01-05-01-01-01-16_to_p334_018/p334_018.wav differ diff --git a/audio/vits_yuqi/EMD6_to_p231_012/EMD6.wav b/audio/vits_yuqi/EMD6_to_p231_012/EMD6.wav new file mode 100644 index 0000000..950252d Binary files /dev/null and b/audio/vits_yuqi/EMD6_to_p231_012/EMD6.wav differ diff --git a/audio/vits_yuqi/EMD6_to_p231_012/EMD6_to_p231_012.wav b/audio/vits_yuqi/EMD6_to_p231_012/EMD6_to_p231_012.wav new file mode 100644 index 0000000..c165d7f Binary files /dev/null and b/audio/vits_yuqi/EMD6_to_p231_012/EMD6_to_p231_012.wav differ diff --git a/audio/vits_yuqi/EMD6_to_p231_012/p231_012.wav b/audio/vits_yuqi/EMD6_to_p231_012/p231_012.wav new file mode 100644 index 0000000..ce55e68 Binary files /dev/null and b/audio/vits_yuqi/EMD6_to_p231_012/p231_012.wav differ diff --git a/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/en-US-ElizabethNeural_1624631702559.wav b/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/en-US-ElizabethNeural_1624631702559.wav new file mode 100644 index 0000000..c73fd0f Binary files /dev/null and b/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/en-US-ElizabethNeural_1624631702559.wav differ diff --git a/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2.wav b/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2.wav new file mode 100644 index 0000000..54dd4a6 Binary files /dev/null and b/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2.wav differ diff --git a/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2_to_en-US-ElizabethNeural_1624631702559.wav b/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2_to_en-US-ElizabethNeural_1624631702559.wav new file mode 100644 index 0000000..1888d63 Binary files /dev/null and b/audio/vits_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2_to_en-US-ElizabethNeural_1624631702559.wav differ diff --git "a/audio/vits_yuqi/\347\224\2672_to_10011/10011.wav" "b/audio/vits_yuqi/\347\224\2672_to_10011/10011.wav" new file mode 100644 index 0000000..930841b Binary files /dev/null and "b/audio/vits_yuqi/\347\224\2672_to_10011/10011.wav" differ diff --git "a/audio/vits_yuqi/\347\224\2672_to_10011/\347\224\2672.wav" "b/audio/vits_yuqi/\347\224\2672_to_10011/\347\224\2672.wav" new file mode 100644 index 0000000..25cc3a8 Binary files /dev/null and "b/audio/vits_yuqi/\347\224\2672_to_10011/\347\224\2672.wav" differ diff --git "a/audio/vits_yuqi/\347\224\2672_to_10011/\347\224\2672_to_10011.wav" "b/audio/vits_yuqi/\347\224\2672_to_10011/\347\224\2672_to_10011.wav" new file mode 100644 index 0000000..0dd165f Binary files /dev/null and "b/audio/vits_yuqi/\347\224\2672_to_10011/\347\224\2672_to_10011.wav" differ diff --git a/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/0011_001750.wav b/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/0011_001750.wav new file mode 100644 index 0000000..7b2a1da Binary files /dev/null and b/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/0011_001750.wav differ diff --git a/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/0011_001750_to_20_205_000031_000000.wav b/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/0011_001750_to_20_205_000031_000000.wav new file mode 100644 index 0000000..dd4e5ab Binary files /dev/null and b/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/0011_001750_to_20_205_000031_000000.wav differ diff --git a/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/20_205_000031_000000.wav b/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/20_205_000031_000000.wav new file mode 100644 index 0000000..43e403e Binary files /dev/null and b/audio/vq_yuqi/0011_001750_to_20_205_000031_000000/20_205_000031_000000.wav differ diff --git a/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16.wav b/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16.wav new file mode 100644 index 0000000..42202e8 Binary files /dev/null and b/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16.wav differ diff --git a/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16_to_p334_018.wav b/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16_to_p334_018.wav new file mode 100644 index 0000000..026a0eb Binary files /dev/null and b/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/03-01-05-01-01-01-16_to_p334_018.wav differ diff --git a/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/p334_018.wav b/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/p334_018.wav new file mode 100644 index 0000000..a397c03 Binary files /dev/null and b/audio/vq_yuqi/03-01-05-01-01-01-16_to_p334_018/p334_018.wav differ diff --git a/audio/vq_yuqi/EMD6_to_p231_012/EMD6.wav b/audio/vq_yuqi/EMD6_to_p231_012/EMD6.wav new file mode 100644 index 0000000..0b815c5 Binary files /dev/null and b/audio/vq_yuqi/EMD6_to_p231_012/EMD6.wav differ diff --git a/audio/vq_yuqi/EMD6_to_p231_012/EMD6_to_p231_012.wav b/audio/vq_yuqi/EMD6_to_p231_012/EMD6_to_p231_012.wav new file mode 100644 index 0000000..0cf7f7f Binary files /dev/null and b/audio/vq_yuqi/EMD6_to_p231_012/EMD6_to_p231_012.wav differ diff --git a/audio/vq_yuqi/EMD6_to_p231_012/p231_012.wav b/audio/vq_yuqi/EMD6_to_p231_012/p231_012.wav new file mode 100644 index 0000000..b1a624c Binary files /dev/null and b/audio/vq_yuqi/EMD6_to_p231_012/p231_012.wav differ diff --git a/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/en-US-ElizabethNeural_1624631702559.wav b/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/en-US-ElizabethNeural_1624631702559.wav new file mode 100644 index 0000000..73500f1 Binary files /dev/null and b/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/en-US-ElizabethNeural_1624631702559.wav differ diff --git a/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2.wav b/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2.wav new file mode 100644 index 0000000..16336b0 Binary files /dev/null and b/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2.wav differ diff --git a/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2_to_en-US-ElizabethNeural_1624631702559.wav b/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2_to_en-US-ElizabethNeural_1624631702559.wav new file mode 100644 index 0000000..19056d7 Binary files /dev/null and b/audio/vq_yuqi/obm2_to_en-US-ElizabethNeural_1624631702559/obm2_to_en-US-ElizabethNeural_1624631702559.wav differ diff --git "a/audio/vq_yuqi/\347\224\2672_to_10011/10011.wav" "b/audio/vq_yuqi/\347\224\2672_to_10011/10011.wav" new file mode 100644 index 0000000..04df0c2 Binary files /dev/null and "b/audio/vq_yuqi/\347\224\2672_to_10011/10011.wav" differ diff --git "a/audio/vq_yuqi/\347\224\2672_to_10011/\347\224\2672.wav" "b/audio/vq_yuqi/\347\224\2672_to_10011/\347\224\2672.wav" new file mode 100644 index 0000000..7142738 Binary files /dev/null and "b/audio/vq_yuqi/\347\224\2672_to_10011/\347\224\2672.wav" differ diff --git "a/audio/vq_yuqi/\347\224\2672_to_10011/\347\224\2672_to_10011.wav" "b/audio/vq_yuqi/\347\224\2672_to_10011/\347\224\2672_to_10011.wav" new file mode 100644 index 0000000..1263fb4 Binary files /dev/null and "b/audio/vq_yuqi/\347\224\2672_to_10011/\347\224\2672_to_10011.wav" differ diff --git a/index.md b/index.md index 8a79244..603ed64 100644 --- a/index.md +++ b/index.md @@ -1,4 +1,5 @@ # FlowCPCVC + ## Audio Demo for "FlowCPCVC:A flow contrastive predictive coding voice conversion system" @@ -645,3 +646,128 @@ ___ + +## The results that wavs are more difficult to convert + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
sourcetargetFlowCPCVCVQMIVC
+ + + + + + + +
+ + + + + + + +
+ + + + + + + +
+ + + + + + + +
+ + + + + + + +
\ No newline at end of file