Upload ParlerTTSForConditionalGeneration

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "output_dir_training-v3/checkpoint-17000-epoch-5",
+  "_name_or_path": "output_mini/checkpoint-16000-epoch-4",
   "architectures": [
     "ParlerTTSForConditionalGeneration"
   ],
   "audio_encoder": {
     "_attn_implementation_autoset": false,
-    "_name_or_path": "ylacombe/dac_44khZ_8kbps",
+    "_name_or_path": "parler-tts/dac_44khZ_8kbps",
     "add_cross_attention": false,
     "architectures": [
       "DACModel"
@@ -77,7 +77,7 @@
   },
   "decoder": {
     "_attn_implementation_autoset": false,
-    "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
+    "_name_or_path": "/fsx/yoach/tmp/artefacts/parler-tts-mini/decoder",
     "activation_dropout": 0.0,
     "activation_function": "gelu",
     "add_cross_attention": true,
@@ -170,7 +170,7 @@
   "prompt_cross_attention": false,
   "text_encoder": {
     "_attn_implementation_autoset": false,
-    "_name_or_path": "google/flan-t5-base",
+    "_name_or_path": "google/flan-t5-large",
     "add_cross_attention": false,
     "architectures": [
       "T5ForConditionalGeneration"
@@ -181,9 +181,9 @@
     "chunk_size_feed_forward": 0,
     "classifier_dropout": 0.0,
     "cross_attention_hidden_size": null,
-    "d_ff": 2048,
+    "d_ff": 2816,
     "d_kv": 64,
-    "d_model": 768,
+    "d_model": 1024,
     "decoder_start_token_id": 0,
     "dense_act_fn": "gelu_new",
     "diversity_penalty": 0.0,
@@ -218,9 +218,9 @@
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_decoder_layers": 12,
-    "num_heads": 12,
-    "num_layers": 12,
+    "num_decoder_layers": 24,
+    "num_heads": 16,
+    "num_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -238,35 +238,7 @@
     "return_dict_in_generate": false,
     "sep_token_id": null,
     "suppress_tokens": null,
-    "task_specific_params": {
-      "summarization": {
-        "early_stopping": true,
-        "length_penalty": 2.0,
-        "max_length": 200,
-        "min_length": 30,
-        "no_repeat_ngram_size": 3,
-        "num_beams": 4,
-        "prefix": "summarize: "
-      },
-      "translation_en_to_de": {
-        "early_stopping": true,
-        "max_length": 300,
-        "num_beams": 4,
-        "prefix": "translate English to German: "
-      },
-      "translation_en_to_fr": {
-        "early_stopping": true,
-        "max_length": 300,
-        "num_beams": 4,
-        "prefix": "translate English to French: "
-      },
-      "translation_en_to_ro": {
-        "early_stopping": true,
-        "max_length": 300,
-        "num_beams": 4,
-        "prefix": "translate English to Romanian: "
-      }
-    },
+    "task_specific_params": null,
     "temperature": 1.0,
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7837edd27e2d71b7979cdcb8fa9d00f7dc71d99c40f91595ba1308fef0d0d71
-size 2588219296
+oid sha256:2a1b5b96a4c1232a4420bc95b352067b13000f2673903e8fa09785db77abba79
+size 3511494464