Upload model

config.json

@@ -1,6 +1,5 @@
 {
   "_commit_hash": null,
-  "_name_or_path": "/home/yoach/bark_weigths/model/",
   "architectures": [
     "BarkModel"
   ],
@@ -45,8 +44,6 @@
     "max_length": 20,
     "min_length": 0,
     "model_type": "coarse_acoustics",
-    "n_codes_given": 1,
-    "n_codes_total": 8,
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
@@ -179,7 +176,8 @@
       2
     ],
     "use_bfloat16": false,
-    "use_causal_conv": true
+    "use_causal_conv": true,
+    "use_conv_shortcut": true
   },
   "fine_acoustics_config": {
     "_name_or_path": "",
@@ -302,8 +300,6 @@
     "max_length": 20,
     "min_length": 0,
     "model_type": "semantic",
-    "n_codes_given": 1,
-    "n_codes_total": 8,
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,

generation_config.json

@@ -23,6 +23,7 @@
     "forced_decoder_ids": null,
     "forced_eos_token_id": null,
     "generation_kwargs": {},
+    "guidance_scale": null,
     "length_penalty": 1.0,
     "max_coarse_history": 630,
     "max_coarse_input_length": 256,
@@ -45,6 +46,7 @@
     "renormalize_logits": true,
     "repetition_penalty": 1.0,
     "return_dict_in_generate": false,
+    "sequence_bias": null,
     "sliding_window_len": 60,
     "suppress_tokens": null,
     "temperature": 0.7,
@@ -76,6 +78,7 @@
     "forced_decoder_ids": null,
     "forced_eos_token_id": null,
     "generation_kwargs": {},
+    "guidance_scale": null,
     "length_penalty": 1.0,
     "max_fine_history_length": 512,
     "max_fine_input_length": 1024,
@@ -98,6 +101,7 @@
     "renormalize_logits": false,
     "repetition_penalty": 1.0,
     "return_dict_in_generate": false,
+    "sequence_bias": null,
     "suppress_tokens": null,
     "temperature": 0.5,
     "top_k": 50,
@@ -129,6 +133,7 @@
     "forced_decoder_ids": null,
     "forced_eos_token_id": null,
     "generation_kwargs": {},
+    "guidance_scale": null,
     "length_penalty": 1.0,
     "max_input_semantic_length": 256,
     "max_length": 20,
@@ -153,6 +158,7 @@
     "semantic_pad_token": 10000,
     "semantic_rate_hz": 49.9,
     "semantic_vocab_size": 10000,
+    "sequence_bias": null,
     "suppress_tokens": null,
     "temperature": 0.7,
     "text_encoding_offset": 10048,
@@ -162,6 +168,5 @@
     "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
     "use_cache": true
-  },
-  "transformers_version": "4.31.0.dev0"
+  }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ac007f13624882c82d561378eb356321594eabf320fdbbe32c25b098dad4df
-size 4516921809
+oid sha256:4e3d407b9b3b619da184c85786c88e5e35f90f9089303e16db696ed0be477989
+size 4486643861