vocals-english-v2 / config.json
AkhilTolani's picture
Upload ParlerTTSForConditionalGeneration
03b44e0 verified
raw
history blame
7.44 kB
{
"_name_or_path": "/mnt/disks/training-data-refine/parler_finetune_run_2",
"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": "4.40.2",
"vocab_size": 32128
}