Upload ParlerTTSForConditionalGeneration

config.json

@@ -1,9 +1,10 @@
 {
-  "_name_or_path": "/fsx/yoach/tmp/artefacts/sweep-50K-large-OG-without-accents-0015/checkpoint-100000-epoch-6/",
+  "_name_or_path": "ylacombe/large_test",
   "architectures": [
     "ParlerTTSForConditionalGeneration"
   ],
   "audio_encoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "ylacombe/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-large-og/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,
@@ -157,6 +160,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
+    "use_fused_lm_heads": false,
     "vocab_size": 1088
   },
   "decoder_start_token_id": 1025,
@@ -165,6 +169,7 @@
   "pad_token_id": 1024,
   "prompt_cross_attention": false,
   "text_encoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "google/flan-t5-xl",
     "add_cross_attention": false,
     "architectures": [
@@ -277,6 +282,6 @@
     "vocab_size": 32128
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
+  "transformers_version": "4.46.1",
   "vocab_size": 32128
 }

generation_config.json

@@ -7,5 +7,5 @@
   "guidance_scale": 1,
   "max_length": 2580,
   "pad_token_id": 1024,
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.46.1"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30d2151a8a9c3343b6998eeec019b46db9d17b84ef234d98ea6723941c2851c
-size 4984365952
+oid sha256:6cfaeabd0f3e3e4431a4c9f6a3b00cc502bb018f485f806ed2f9817bb561daed
+size 4984368376

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:413db5baa97486c7447a4060bb2ced9235d1785d51ac981e0880eff2cb044ca5
-size 4347810672
+oid sha256:bb14c68411cfc03039e5f4ed7b90b7a8dea1e220b78adfa07ceb3bf4cfc32f23
+size 4347812152

model.safetensors.index.json

@@ -4,306 +4,306 @@
   },
   "weight_map": {
     "audio_encoder.model.decoder.model.0.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.0.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.0.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.0.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.0.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.2.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.2.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.2.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.2.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.3.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.3.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.3.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.3.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.4.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.4.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.4.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.1.block.4.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.2.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.2.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.2.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.2.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.3.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.3.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.3.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.3.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.4.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.4.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.4.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.2.block.4.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.2.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.2.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.2.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.2.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.3.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.3.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.3.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.3.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.4.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.4.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.4.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.3.block.4.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.2.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.2.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.2.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.2.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.3.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.3.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.3.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.3.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.4.block.0.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.4.block.1.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.1.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.1.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.4.block.2.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.4.block.4.block.3.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.3.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.3.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.5.alpha": "model-00002-of-00002.safetensors",
     "audio_encoder.model.decoder.model.6.bias": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.6.weight_g": "model-00002-of-00002.safetensors",
-    "audio_encoder.model.decoder.model.6.weight_v": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.6.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
+    "audio_encoder.model.decoder.model.6.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
     "audio_encoder.model.encoder.block.0.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.0.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.0.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.0.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.0.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.0.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.0.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.0.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.0.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.0.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.0.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.0.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.0.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.0.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.0.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.0.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.0.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.1.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.1.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.1.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.1.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.1.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.1.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.1.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.1.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.1.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.1.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.1.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.1.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.2.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.2.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.2.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.2.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.2.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.2.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.2.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.2.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.2.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.2.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.2.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.2.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.3.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.1.block.4.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.4.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.1.block.4.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.4.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.1.block.4.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.0.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.0.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.0.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.0.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.0.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.0.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.0.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.0.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.0.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.0.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.0.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.0.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.1.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.1.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.1.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.1.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.1.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.1.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.1.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.1.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.1.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.1.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.1.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.1.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.2.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.2.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.2.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.2.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.2.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.2.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.2.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.2.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.2.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.2.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.2.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.2.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.3.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.2.block.4.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.4.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.2.block.4.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.4.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.2.block.4.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.0.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.0.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.0.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.0.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.0.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.0.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.0.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.0.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.0.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.0.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.0.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.0.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.1.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.1.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.1.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.1.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.1.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.1.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.1.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.1.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.1.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.1.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.1.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.1.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.2.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.2.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.2.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.2.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.2.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.2.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.2.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.2.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.2.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.2.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.2.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.2.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.3.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.3.block.4.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.4.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.3.block.4.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.4.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.3.block.4.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.0.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.0.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.0.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.0.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.0.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.0.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.0.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.0.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.0.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.0.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.0.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.0.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.1.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.1.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.1.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.1.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.1.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.1.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.1.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.1.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.1.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.1.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.1.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.1.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.2.block.0.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.2.block.1.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.2.block.1.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.2.block.1.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.2.block.1.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.2.block.1.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.2.block.2.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.2.block.3.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.2.block.3.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.2.block.3.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.2.block.3.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.2.block.3.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.3.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.4.block.4.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.4.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.4.block.4.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.4.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.4.block.4.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.5.alpha": "model-00001-of-00002.safetensors",
     "audio_encoder.model.encoder.block.6.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.6.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.encoder.block.6.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.6.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.encoder.block.6.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.0.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.0.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.0.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.0.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.0.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.0.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.0.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.0.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.0.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.0.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.0.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.1.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.1.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.1.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.1.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.1.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.1.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.1.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.1.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.1.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.1.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.1.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.2.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.2.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.2.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.2.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.2.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.2.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.2.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.2.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.2.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.2.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.2.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.3.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.3.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.3.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.3.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.3.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.3.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.3.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.3.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.3.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.3.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.3.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.4.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.4.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.4.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.4.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.4.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.4.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.4.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.4.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.4.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.4.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.4.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.5.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.5.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.5.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.5.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.5.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.5.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.5.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.5.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.5.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.5.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.5.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.6.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.6.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.6.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.6.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.6.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.6.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.6.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.6.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.6.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.6.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.6.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.7.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.7.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.7.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.7.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.7.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.7.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.7.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.7.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.7.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.7.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.7.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.8.codebook.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.8.in_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.8.in_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.8.in_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.8.in_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.8.in_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "audio_encoder.model.quantizer.quantizers.8.out_proj.bias": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.8.out_proj.weight_g": "model-00001-of-00002.safetensors",
-    "audio_encoder.model.quantizer.quantizers.8.out_proj.weight_v": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.8.out_proj.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
+    "audio_encoder.model.quantizer.quantizers.8.out_proj.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
     "decoder.lm_heads.0.weight": "model-00002-of-00002.safetensors",
     "decoder.lm_heads.1.weight": "model-00002-of-00002.safetensors",
     "decoder.lm_heads.2.weight": "model-00002-of-00002.safetensors",