add more

age_gender/w2v2-L-robust-6-age-gender.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c5cc3debc2013215cee5f331a66b59bd7205da170fb61abab46fc4507df7be
+size 363421332

hubert/DPHuBERT-sp0.75.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384d72429163b79cd9f4deaf41aa2cbc990e7526b4430f2a22d40c5e70c14be7
+size 99132650

hubert/hubert_base.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b40fd2802423a5643779c4861af1e9ee9c1564dc9d32f54f20b5ffba7db96
+size 189507909

hubert/hubert_base_12_768.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb3e1787cecc78023fa40c7ace8897b7bcce093d8d4b5ea4357e3cee23f1f32
+size 384166505

hubert/hubert_base_12_768_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754d85e95f5a97ea45cac275875524b588529a1d926db140dbac3c8ce1fe0020
+size 195568997

hubert/hubert_base_9_256_proj_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86b7dfb677ee0391e470b8372b13a57d5fcbb1709b6a609aacd4b1e50568406
+size 151293032

hubert/hubert_base_ailia_2_output.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7aaee8684892f54ff181b46d2f4e8aef7684af76be7713346844b8de924dedf
+size 293548373

rmvpe/crepe_onnx_full.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119845c72c702e052e5262430f9d120bce46176689aa226c39d09dea5cc3a610
+size 88984790

rmvpe/crepe_onnx_tiny.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91fc2a0fd10f965dbf7775995daf50e99273caedd7efd00001f23be649da1bc3
+size 1955762

rmvpe/fcpe.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988522bdee2b0954ec5d43eb3fd6805c7a7d05cd8198a031e6ca67251bdbb872
+size 43917245

rmvpe/fcpe_cents_include.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e991f1077bbbadb222b718b0434360a1aff1b1916c943ef1285b996895e385
+size 43768220

rmvpe/rmvpe.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5370e71ac80af8b4b7c793d27efd51fd8bf962de3a7ede0766dac0befa3660fd
+size 361688443

rmvpe/rmvpe.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d62215f4306e3ca278246188607209f09af3dc77ed4232efdd069798c4ec193
+size 181184272

rmvpe/rmvpe_230917.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19dc1809cf4cdb0a18db93441816bc327e14e5644b72eeaae5220560c6736fe2
+size 368492925

rmvpe/rmvpe_inputs.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339fcb7e1476b302e9aecef4a951e918c20852b2e871de5eea13b06e554e0a3a
+size 33527

rmvpe/rmvpe_mel_include.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f0586308e36157f75b77c8591bf636d6719c0c4ba95f8faf3df479e7566219
+size 362003174

{speak_detect → speak_detection}/snakers4_silero-vad_master/utils_vad.py

@@ -132,31 +132,34 @@ class Validator():
 
 def read_audio(path: str,
                sampling_rate: int = 16000):
-    list_backends = torchaudio.list_audio_backends()
-    
-    assert len(list_backends) > 0, 'The list of available backends is empty, please install backend manually. \
-                                    \n Recommendations: \n \tSox (UNIX OS) \n \tSoundfile (Windows OS, UNIX OS) \n \tffmpeg (Windows OS, UNIX OS)'
-
-    try:
-        effects = [
-            ['channels', '1'],
-            ['rate', str(sampling_rate)]
-        ]
-
-        wav, sr = torchaudio.sox_effects.apply_effects_file(path, effects=effects)
-    except:
-        wav, sr = torchaudio.load(path)
-
-        if wav.size(0) > 1:
-            wav = wav.mean(dim=0, keepdim=True)
-
-        if sr != sampling_rate:
-            transform = torchaudio.transforms.Resample(orig_freq=sr,
-                                                       new_freq=sampling_rate)
-            wav = transform(wav)
-            sr = sampling_rate
-
-    assert sr == sampling_rate
+    if isinstance(path, np.ndarray):
+        wav = torch.tensor(path.reshape(1, -1))
+    else:
+        list_backends = torchaudio.list_audio_backends()
+
+        assert len(list_backends) > 0, 'The list of available backends is empty, please install backend manually. \
+                                        \n Recommendations: \n \tSox (UNIX OS) \n \tSoundfile (Windows OS, UNIX OS) \n \tffmpeg (Windows OS, UNIX OS)'
+
+        try:
+            effects = [
+                ['channels', '1'],
+                ['rate', str(sampling_rate)]
+            ]
+
+            wav, sr = torchaudio.sox_effects.apply_effects_file(path, effects=effects)
+        except:
+            wav, sr = torchaudio.load(path)
+
+            if wav.size(0) > 1:
+                wav = wav.mean(dim=0, keepdim=True)
+
+            if sr != sampling_rate:
+                transform = torchaudio.transforms.Resample(orig_freq=sr,
+                                                           new_freq=sampling_rate)
+                wav = transform(wav)
+                sr = sampling_rate
+
+        assert sr == sampling_rate
     return wav.squeeze(0)