Upload folder using huggingface_hub

.gitattributes

@@ -58,3 +58,11 @@ outputs/zh_long_paragraph.wav filter=lfs diff=lfs merge=lfs -text
 outputs/zh_long_paragraph_distill_ax650.wav filter=lfs diff=lfs merge=lfs -text
 outputs/zh_sentence.wav filter=lfs diff=lfs merge=lfs -text
 outputs/zh_sentence_distill_ax650.wav filter=lfs diff=lfs merge=lfs -text
+en_long_paragraph_ax650.wav filter=lfs diff=lfs merge=lfs -text
+en_long_paragraph_distill_ax650.wav filter=lfs diff=lfs merge=lfs -text
+en_sentence_ax650.wav filter=lfs diff=lfs merge=lfs -text
+en_sentence_distill_ax650.wav filter=lfs diff=lfs merge=lfs -text
+zh_long_paragraph_ax650.wav filter=lfs diff=lfs merge=lfs -text
+zh_long_paragraph_distill_ax650.wav filter=lfs diff=lfs merge=lfs -text
+zh_sentence_ax650.wav filter=lfs diff=lfs merge=lfs -text
+zh_sentence_distill_ax650.wav filter=lfs diff=lfs merge=lfs -text

configs/decoder4_split_manifest.json

@@ -1,74 +0,0 @@
-{
-    "version": 2,
-    "source_summary": "/data/huyuan/workspace/LLM/TTS/ZIPVOICE_RICH_CHECK0_REQUANT_SUMMARY.md",
-    "source_static_onnx_manifest": "/data/huyuan/workspace/LLM/TTS/ZipVoice.AXERA/models/static_mask_1024_cfgfix_nolog_encoder_attn_loop_sigmoid_bump_decoder4/decoder4_split_manifest.json",
-    "source_encoder_axmodel": "/data/huyuan/workspace/LLM/TTS/ZipVoice.AXERA/model_convert/axmodels_nolog_encoder_core_rich_check0/encoder_core_nolog_rich_check0.axmodel",
-    "source_decoder_axmodel_dir": "/data/huyuan/workspace/LLM/TTS/ZipVoice.AXERA/model_convert/axmodels_attn_loop_sigmoid_bump_decoder4_rich_check0",
-    "encoder": {
-        "name": "encoder_core",
-        "file": "encoder.axmodel",
-        "inputs": [
-            "cat_tokens"
-        ],
-        "outputs": [
-            "encoded"
-        ]
-    },
-    "decoder_parts": [
-        {
-            "name": "fm_decoder_part0",
-            "file": "decoder_part0.axmodel",
-            "inputs": [
-                "t",
-                "x",
-                "text_condition",
-                "speech_condition",
-                "guidance_scale",
-                "padding_mask"
-            ],
-            "outputs": [
-                "decoder_hidden_p0",
-                "time_hidden",
-                "padding_mask2",
-                "cfg_scale"
-            ]
-        },
-        {
-            "name": "fm_decoder_part1",
-            "file": "decoder_part1.axmodel",
-            "inputs": [
-                "decoder_hidden_p0",
-                "time_hidden",
-                "padding_mask2"
-            ],
-            "outputs": [
-                "decoder_hidden_p1"
-            ]
-        },
-        {
-            "name": "fm_decoder_part2",
-            "file": "decoder_part2.axmodel",
-            "inputs": [
-                "decoder_hidden_p1",
-                "time_hidden",
-                "padding_mask2"
-            ],
-            "outputs": [
-                "decoder_hidden_p2"
-            ]
-        },
-        {
-            "name": "fm_decoder_part3",
-            "file": "decoder_part3.axmodel",
-            "inputs": [
-                "decoder_hidden_p2",
-                "time_hidden",
-                "padding_mask2",
-                "cfg_scale"
-            ],
-            "outputs": [
-                "v"
-            ]
-        }
-    ]
-}

configs/runtime_config.json

@@ -1,12 +0,0 @@
-{
-    "model_type": "zipvoice_decoder4",
-    "max_tokens": 384,
-    "max_feat_len": 1024,
-    "feat_dim": 100,
-    "sampling_rate": 24000,
-    "hop_length": 256,
-    "num_step": 16,
-    "t_shift": 0.5,
-    "guidance_scale": 1.0,
-    "speed": 1.0
-}

en_long_paragraph_distill_ax650.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b90489242cb1cd03458530308d67b719cc5d5b891385ff87822d31e5a63f71
+size 3108012

en_sentence_ax650.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc94c226559874053edde5331913364b6e2cd01ef7dde58e3c8df7735296e377
+size 307756

en_sentence_distill_ax650.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb79eddf831f530450d2c5f7c4dee0d8a1f5e7ddbbe633f94defed8a4e9ddc6f
+size 307756

zh_long_paragraph_ax650.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6805938a16e5b4a257444c2b33897ffba0d3a5cdbdb7a2de9dd93dd629273947
+size 2147756

zh_long_paragraph_distill_ax650.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7595cfd42e8aa9ad2a97955776262ba87565bd182a9d5e757510b0c5f49c8b3
+size 2147756

zh_sentence_ax650.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2997789e759fd6852ea30c73226d04a09369dabb777244c75d641798b09f1dab
+size 307756

zh_sentence_distill_ax650.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897608a94506534cb60ce9ba8106735b22ccf8cf7b4e48b04a5a1674be876d2d
+size 307756