Initial

config.json

@@ -1,9 +1,10 @@
 {
-    "_name_or_path": "bigband/ToweringDumuzi",
+    "_name_or_path": "UrbanAlchemie/johnson_2",
     "architectures": [
         "ParlerTTSForConditionalGeneration"
     ],
     "audio_encoder": {
+        "_attn_implementation_autoset": false,
         "_name_or_path": "parler-tts/dac_44khZ_8kbps",
         "add_cross_attention": false,
         "architectures": [
@@ -41,7 +42,7 @@
         "max_length": 20,
         "min_length": 0,
         "model_bitrate": 8,
-        "model_type": "dac",
+        "model_type": "dac_on_the_hub",
         "no_repeat_ngram_size": 0,
         "num_beam_groups": 1,
         "num_beams": 1,
@@ -75,6 +76,7 @@
         "use_bfloat16": false
     },
     "decoder": {
+        "_attn_implementation_autoset": false,
         "_name_or_path": "/fsx/yoach/tmp/artefacts/parler-tts-mini/decoder",
         "activation_dropout": 0.0,
         "activation_function": "gelu",
@@ -87,6 +89,7 @@
         "begin_suppress_tokens": null,
         "bos_token_id": 1025,
         "chunk_size_feed_forward": 0,
+        "codebook_weights": null,
         "cross_attention_hidden_size": null,
         "cross_attention_implementation_strategy": null,
         "decoder_start_token_id": null,
@@ -116,7 +119,7 @@
         "layerdrop": 0.0,
         "length_penalty": 1.0,
         "max_length": 20,
-        "max_position_embeddings": 4096,
+        "max_position_embeddings": 4311,
         "min_length": 0,
         "model_type": "parler_tts_decoder",
         "no_repeat_ngram_size": 0,
@@ -157,14 +160,19 @@
         "typical_p": 1.0,
         "use_bfloat16": false,
         "use_cache": true,
+        "use_fused_lm_heads": false,
         "vocab_size": 1088
     },
     "decoder_start_token_id": 1025,
+    "fine_tuned": true,
+    "hidden_dropout_prob": 0.0001,
     "is_encoder_decoder": true,
     "model_type": "parler_tts",
+    "model_version": "1.1-modified",
     "pad_token_id": 1024,
     "prompt_cross_attention": false,
     "text_encoder": {
+        "_attn_implementation_autoset": false,
         "_name_or_path": "google/flan-t5-large",
         "add_cross_attention": false,
         "architectures": [
@@ -249,6 +257,6 @@
         "vocab_size": 32128
     },
     "torch_dtype": "float32",
-    "transformers_version": "4.43.3",
+    "transformers_version": "4.46.1",
     "vocab_size": 32128
 }

generation_config.json

@@ -5,8 +5,8 @@
   "do_sample": true,
   "eos_token_id": 1024,
   "guidance_scale": 1,
-  "max_length": 2580,
+  "max_length": 4150,
   "min_new_tokens": 10,
   "pad_token_id": 1024,
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.46.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94da905b2e521ce504f992f8b3d950bad3393a617186d348d36bded4ada3932
-size 3511490600
+oid sha256:5b9ae10e640f56f36b2a786a954597002766ae80b4879905cc554d55f81e7105
+size 3512375104

tokenizer_config.json

@@ -927,7 +927,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,