remove whispering

.gitattributes

@@ -33,53 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_117_3f7a73b6eb939439853b.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_117_51c4feb7b25049501e37.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_117_6d818be44006fe311b25.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_117_7633a61e6ee80a024fb2.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_117_855fad46eee4554f15a7.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_117_dd8bdcb385062c83d9db.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_117_ea76ce7bbfab47610005.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_195_2abe63a219dd9980a311.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_195_69610571800405c8afc4.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_195_6cac4adea8fad0e75539.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_195_830d908cf01e69e53001.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_195_83726d791dfb671cadab.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_195_c0a3f3d7cd9b5e6f1ff3.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_195_c762fd4cdeb8dd603c93.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_234_07ddb3b15d19fc0d28b8.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_234_081798576741dcab4ed7.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_234_1c742d222224ecad309d.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_234_823c293a773a7747aae9.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_234_b9550b7eaa369565c70f.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_234_c4854e1ae7d92c3a58d5.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_234_e8462d5ee69db7355157.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_273_1b11908a3b16b03f6f28.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_273_623fa20cd98668542c5a.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_273_7e85e65244c43352d3ff.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_273_85b843d1a8a6ba22faee.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_273_89094caf461fb7b67ec7.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_273_8f6478a9918ad2b1ae55.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_273_9f4846c46a52d5e23c8d.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_312_01c26787b801562a3789.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_312_0ceabcd2840ac8898fe1.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_312_337071167ae9bad07b71.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_312_43fb61bde32a4b6742d4.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_312_47c9ee8dc54086885fe9.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_312_ac7b82097e1e55d1368c.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_312_f460b32c3554b8680b92.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_39_6481b4598446a5223728.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_39_65c5863263ecc0063e7c.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_39_75f77b4060ad41f6cd28.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_39_91ec273933f07274531b.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_39_a92c59803d84d120f9c8.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_39_e334e92b9d2007210460.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_39_e93fbf8d0314875d9a8a.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_78_2a1aa9c4aa9b28aeff3d.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_78_31d4a3506990aa644012.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_78_6f247990e446903b7c69.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_78_ccbbfb2e4ad764ed2d56.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_78_e0a9392514f4f0b15b68.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_78_e8936f475da43789ec82.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/files/media/audio/Speech[[:space:]]samples/eval_78_ff389c0afad3d276441d.wav filter=lfs diff=lfs merge=lfs -text
-wandb/run-20240513_205708-e3sq5zz5/run-e3sq5zz5.wandb filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+wandb

checkpoint-144-epoch-3/config.json

@@ -0,0 +1,276 @@
+{
+  "_name_or_path": "/fsx/yoach/tmp/artefacts/training-400M-punctuated-v2/",
+  "architectures": [
+    "ParlerTTSForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "ylacombe/dac_44khZ_8kbps",
+    "add_cross_attention": false,
+    "architectures": [
+      "DACModel"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_size": 1024,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "frame_rate": 86,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_dim": 1024,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_bitrate": 8,
+    "model_type": "dac",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 44100,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "decoder": {
+    "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "ParlerTTSForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1025,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1024,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "parler_tts_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1024,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1088
+  },
+  "decoder_start_token_id": 1025,
+  "is_encoder_decoder": true,
+  "model_type": "parler_tts",
+  "pad_token_id": 1024,
+  "text_encoder": {
+    "_name_or_path": "google/flan-t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "gated-gelu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "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: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vocab_size": 32128
+}

checkpoint-144-epoch-3/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1025,
+  "decoder_start_token_id": 1025,
+  "do_sample": true,
+  "eos_token_id": 1024,
+  "guidance_scale": 1.0,
+  "max_length": 2580,
+  "min_new_tokens": 50,
+  "pad_token_id": 1024,
+  "transformers_version": "4.41.0.dev0"
+}

checkpoint-216-epoch-5/config.json

@@ -0,0 +1,276 @@
+{
+  "_name_or_path": "/fsx/yoach/tmp/artefacts/training-400M-punctuated-v2/",
+  "architectures": [
+    "ParlerTTSForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "ylacombe/dac_44khZ_8kbps",
+    "add_cross_attention": false,
+    "architectures": [
+      "DACModel"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_size": 1024,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "frame_rate": 86,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_dim": 1024,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_bitrate": 8,
+    "model_type": "dac",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 44100,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "decoder": {
+    "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "ParlerTTSForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1025,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1024,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "parler_tts_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1024,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1088
+  },
+  "decoder_start_token_id": 1025,
+  "is_encoder_decoder": true,
+  "model_type": "parler_tts",
+  "pad_token_id": 1024,
+  "text_encoder": {
+    "_name_or_path": "google/flan-t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "gated-gelu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "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: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vocab_size": 32128
+}

checkpoint-216-epoch-5/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1025,
+  "decoder_start_token_id": 1025,
+  "do_sample": true,
+  "eos_token_id": 1024,
+  "guidance_scale": 1.0,
+  "max_length": 2580,
+  "min_new_tokens": 50,
+  "pad_token_id": 1024,
+  "transformers_version": "4.41.0.dev0"
+}

checkpoint-288-epoch-7/config.json

@@ -0,0 +1,276 @@
+{
+  "_name_or_path": "/fsx/yoach/tmp/artefacts/training-400M-punctuated-v2/",
+  "architectures": [
+    "ParlerTTSForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "ylacombe/dac_44khZ_8kbps",
+    "add_cross_attention": false,
+    "architectures": [
+      "DACModel"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_size": 1024,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "frame_rate": 86,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_dim": 1024,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_bitrate": 8,
+    "model_type": "dac",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 44100,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "decoder": {
+    "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "ParlerTTSForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1025,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1024,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "parler_tts_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1024,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1088
+  },
+  "decoder_start_token_id": 1025,
+  "is_encoder_decoder": true,
+  "model_type": "parler_tts",
+  "pad_token_id": 1024,
+  "text_encoder": {
+    "_name_or_path": "google/flan-t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "gated-gelu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "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: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vocab_size": 32128
+}

checkpoint-288-epoch-7/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1025,
+  "decoder_start_token_id": 1025,
+  "do_sample": true,
+  "eos_token_id": 1024,
+  "guidance_scale": 1.0,
+  "max_length": 2580,
+  "min_new_tokens": 50,
+  "pad_token_id": 1024,
+  "transformers_version": "4.41.0.dev0"
+}

checkpoint-312-epoch-7/config.json

@@ -0,0 +1,276 @@
+{
+  "_name_or_path": "/fsx/yoach/tmp/artefacts/training-400M-punctuated-v2/",
+  "architectures": [
+    "ParlerTTSForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "ylacombe/dac_44khZ_8kbps",
+    "add_cross_attention": false,
+    "architectures": [
+      "DACModel"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_size": 1024,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "frame_rate": 86,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_dim": 1024,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_bitrate": 8,
+    "model_type": "dac",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 44100,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "decoder": {
+    "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "ParlerTTSForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1025,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1024,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "parler_tts_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1024,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1088
+  },
+  "decoder_start_token_id": 1025,
+  "is_encoder_decoder": true,
+  "model_type": "parler_tts",
+  "pad_token_id": 1024,
+  "text_encoder": {
+    "_name_or_path": "google/flan-t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "gated-gelu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "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: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vocab_size": 32128
+}

checkpoint-312-epoch-7/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1025,
+  "decoder_start_token_id": 1025,
+  "do_sample": true,
+  "eos_token_id": 1024,
+  "guidance_scale": 1.0,
+  "max_length": 2580,
+  "min_new_tokens": 50,
+  "pad_token_id": 1024,
+  "transformers_version": "4.41.0.dev0"
+}

checkpoint-72-epoch-1/config.json

@@ -0,0 +1,276 @@
+{
+  "_name_or_path": "/fsx/yoach/tmp/artefacts/training-400M-punctuated-v2/",
+  "architectures": [
+    "ParlerTTSForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "ylacombe/dac_44khZ_8kbps",
+    "add_cross_attention": false,
+    "architectures": [
+      "DACModel"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_size": 1024,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "frame_rate": 86,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_dim": 1024,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_bitrate": 8,
+    "model_type": "dac",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 44100,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "decoder": {
+    "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "ParlerTTSForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1025,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1024,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "parler_tts_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1024,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1088
+  },
+  "decoder_start_token_id": 1025,
+  "is_encoder_decoder": true,
+  "model_type": "parler_tts",
+  "pad_token_id": 1024,
+  "text_encoder": {
+    "_name_or_path": "google/flan-t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "gated-gelu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "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: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vocab_size": 32128
+}

checkpoint-72-epoch-1/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1025,
+  "decoder_start_token_id": 1025,
+  "do_sample": true,
+  "eos_token_id": 1024,
+  "guidance_scale": 1.0,
+  "max_length": 2580,
+  "min_new_tokens": 50,
+  "pad_token_id": 1024,
+  "transformers_version": "4.41.0.dev0"
+}

run.sh

@@ -49,4 +49,5 @@ accelerate launch ./run_parler_tts_training.py \
     --save_steps 72 \
     --evaluation_strategy "epoch" \
     --save_total_limit 5 \
-    --group_by_length true
+    --group_by_length true \
+    --push_to_hub

run_parler_tts_training.py

@@ -942,6 +942,7 @@ def main():
         columns_to_keep = {
             "target_audio_column_name": data_args.target_audio_column_name,
             "prompt_column_name": data_args.prompt_column_name,
+            "style": "style",
         }
         if data_args.description_column_name is not None:
             columns_to_keep["description_column_name"] = data_args.description_column_name
@@ -1019,6 +1020,12 @@ def main():
             ),
         }
     )
+    
+    if not dataset_was_precomputed:
+        def remove_whispering(style):
+            return style != "whisper"
+    
+        raw_datasets = raw_datasets.filter(remove_whispering)
 
     # create model
     model = ParlerTTSForConditionalGeneration.from_pretrained(
@@ -1028,6 +1035,7 @@ def main():
         token=data_args.token,
         trust_remote_code=data_args.trust_remote_code,
     )
+    generation_config = model.generation_config
 
     # enable gradient checkpointing if necessary
     if training_args.gradient_checkpointing:
@@ -1619,6 +1627,8 @@ def main():
                     # https://github.com/huggingface/transformers/issues/27293#issuecomment-1872560074
                     accelerator.save_state(output_dir=intermediate_dir, safe_serialization=False)
                     accelerator.wait_for_everyone()
+                    config.save_pretrained(intermediate_dir)
+                    generation_config.save_pretrained(intermediate_dir)
                     if accelerator.is_main_process:
                         rotate_checkpoints(training_args.save_total_limit, output_dir=training_args.output_dir)
 
@@ -1761,3 +1771,4 @@ def main():
 if __name__ == "__main__":
     set_start_method("spawn")
     main()
+