Upload folder using huggingface_hub

config.json

@@ -1,10 +1,10 @@
 {
-  "_name_or_path": "/fsx/yoach/tmp/artefacts/training-PES24-TTS-v3/",
+  "_name_or_path": "/fsx/yoach/tmp/artefacts/training-50K-mini-without-accents-3-mononode/",
   "architectures": [
     "ParlerTTSForConditionalGeneration"
   ],
   "audio_encoder": {
-    "_name_or_path": "ylacombe/dac_44khZ_8kbps",
+    "_name_or_path": "parler-tts/dac_44khZ_8kbps",
     "add_cross_attention": false,
     "architectures": [
       "DACModel"
@@ -75,7 +75,7 @@
     "use_bfloat16": false
   },
   "decoder": {
-    "_name_or_path": "/fsx/yoach/tmp/artefacts/parler-tts-large-og/decoder",
+    "_name_or_path": "/fsx/yoach/tmp/artefacts/parler-tts-mini/decoder",
     "activation_dropout": 0.0,
     "activation_function": "gelu",
     "add_cross_attention": true,
@@ -97,11 +97,11 @@
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 1024,
     "exponential_decay_length_penalty": null,
-    "ffn_dim": 6144,
+    "ffn_dim": 4096,
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
-    "hidden_size": 1536,
+    "hidden_size": 1024,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
@@ -120,13 +120,13 @@
     "min_length": 0,
     "model_type": "parler_tts_decoder",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 24,
+    "num_attention_heads": 16,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_codebooks": 9,
-    "num_cross_attention_key_value_heads": 24,
-    "num_hidden_layers": 25,
-    "num_key_value_heads": 24,
+    "num_cross_attention_key_value_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -165,7 +165,7 @@
   "pad_token_id": 1024,
   "prompt_cross_attention": false,
   "text_encoder": {
-    "_name_or_path": "google/flan-t5-xl",
+    "_name_or_path": "google/flan-t5-large",
     "add_cross_attention": false,
     "architectures": [
       "T5ForConditionalGeneration"
@@ -176,9 +176,9 @@
     "chunk_size_feed_forward": 0,
     "classifier_dropout": 0.0,
     "cross_attention_hidden_size": null,
-    "d_ff": 5120,
+    "d_ff": 2816,
     "d_kv": 64,
-    "d_model": 2048,
+    "d_model": 1024,
     "decoder_start_token_id": 0,
     "dense_act_fn": "gelu_new",
     "diversity_penalty": 0.0,
@@ -214,7 +214,7 @@
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_decoder_layers": 24,
-    "num_heads": 32,
+    "num_heads": 16,
     "num_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -233,35 +233,7 @@
     "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,
@@ -269,7 +241,7 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
     "typical_p": 1.0,
     "use_bfloat16": false,
@@ -277,6 +249,6 @@
     "vocab_size": 32128
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
+  "transformers_version": "4.40.2",
   "vocab_size": 32128
 }

generation_config.json

@@ -2,10 +2,11 @@
   "_from_model_config": true,
   "bos_token_id": 1025,
   "decoder_start_token_id": 1025,
+  "min_new_tokens": 10,
   "do_sample": true,
   "eos_token_id": 1024,
   "guidance_scale": 1,
   "max_length": 2580,
   "pad_token_id": 1024,
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.40.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd34c3307ec21e0d7c8b46afb092250cc9732963deb92be094c095fbb473fc71
+size 3511490560