Upload folder using huggingface_hub

models/.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,48 @@
+{
+    "resblock": "1",
+    "num_gpus": 3,
+    "batch_size": 60,
+    "learning_rate": 0.0001,
+    "adam_b1": 0.5,
+    "adam_b2": 0.9,
+    "lr_decay": 0.98,
+    "seed": 1234,
+    "lambda_distill": 0.15,
+
+    "n_filters": 64,
+    "strides": [8,5,4,2],
+    "dimension": 1024,
+    "semantic_dimension": 768,
+    "bidirectional": true,
+    "dilation_base": 2,
+    "residual_kernel_size": 3,
+    "n_residual_layers": 1,
+    "lstm_layers": 2,
+    "activation": "ELU",
+
+
+    "segment_size": 48000,
+    "num_mels": 80,
+    "num_freq": 1025,
+    "n_fft": 1024,
+    "hop_size": 240,
+    "win_size": 1024,
+
+    "sampling_rate": 16000,
+    "sample_rate": 16000,
+
+    "codebook_size": 1024,
+    "n_q": 8,
+
+    "fmin": 0,
+    "fmax": 8000,
+    "fmax_for_loss": null,
+
+    "num_workers": 12,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54322",
+        "world_size": 1
+    }
+}

models/checkpoint-10000/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1877,
+  "pad_token_id": 1026,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 6027
+}

models/checkpoint-10000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 1026,
+  "transformers_version": "4.41.2"
+}

models/checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71210d9cf05a4a71355518f1db65691da071bfe0ad4915c62287c0179f769778
+size 364520064

models/checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a40385edf3632f109407116c8abd0d09997740d5df389f052283035aed5a10b
+size 729134010

models/checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4ba3793dc249607794ec829c5ea04db1de200de17944eece563c95795e2ee8
+size 14244

models/checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082303d814e0ecbb2362009f05712441bc4dd59741b38d940cb9613ca211fb09
+size 1064

models/checkpoint-10000/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab476b2a193a8bb001f6e0c70ae3640ae41d93adf15e6543544ac2aba8e1587f
+size 5112

models/ckpt_librispeech_clean.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11edfb7f9c4fc84d7b2930855efe94aeabeaae3cd99d849f4015f2241b5e6fbc
+size 1170787339

models/ckpt_librispeech_other.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4bcf9d781f9157bff3342fe77381230869ce30832fce779972d6036f0740e65
+size 1509396715

models/config.json

@@ -0,0 +1,48 @@
+{
+    "resblock": "1",
+    "num_gpus": 3,
+    "batch_size": 60,
+    "learning_rate": 0.0001,
+    "adam_b1": 0.5,
+    "adam_b2": 0.9,
+    "lr_decay": 0.98,
+    "seed": 1234,
+    "lambda_distill": 0.15,
+
+    "n_filters": 64,
+    "strides": [8,5,4,2],
+    "dimension": 1024,
+    "semantic_dimension": 768,
+    "bidirectional": true,
+    "dilation_base": 2,
+    "residual_kernel_size": 3,
+    "n_residual_layers": 1,
+    "lstm_layers": 2,
+    "activation": "ELU",
+
+
+    "segment_size": 48000,
+    "num_mels": 80,
+    "num_freq": 1025,
+    "n_fft": 1024,
+    "hop_size": 240,
+    "win_size": 1024,
+
+    "sampling_rate": 16000,
+    "sample_rate": 16000,
+
+    "codebook_size": 1024,
+    "n_q": 8,
+
+    "fmin": 0,
+    "fmax": 8000,
+    "fmax_for_loss": null,
+
+    "num_workers": 12,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54322",
+        "world_size": 1
+    }
+}

models/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f987b64ae39991d8cb84e736a3a3d8813d8139809bbdcfdf8b2990ed4d6b440b
+size 970027718

models/tokenizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04593b6c9a4b475f91ca481141a6ef5b23e6ac112f347dd2b2717f193c1c728
+size 481906997

models/vocoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d1f7188b95b06304bc05e524fddf93c7fe682fdd93acff022685663a5e26b97
+size 54051213

models/vocoder_config.json

@@ -0,0 +1,53 @@
+{
+    "input_wavs_dir": "/private/home/adampolyak/datasets/LJ/LJSpeech-1.1/wavs_16khz_padded",
+    "input_training_file": "/large_experiments/ust/annl/datasets/tts/LJSpeech/filelist/mhubert_vp_en_es_fr_it3_400k/lj_train_layer11_hubert1000_filelist.txt",
+    "input_validation_file": "/large_experiments/ust/annl/datasets/tts/LJSpeech/filelist/mhubert_vp_en_es_fr_it3_400k/lj_dev_layer11_hubert1000_filelist.txt",
+
+    "resblock": "1",
+    "num_gpus": 0,
+    "batch_size": 16,
+    "learning_rate": 0.0002,
+    "adam_b1": 0.8,
+    "adam_b2": 0.99,
+    "lr_decay": 0.999,
+    "seed": 1234,
+
+    "upsample_rates": [5,4,4,2,2],
+    "upsample_kernel_sizes": [11,8,8,4,4],
+    "upsample_initial_channel": 512,
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "num_embeddings": 1000,
+    "embedding_dim": 128,
+    "model_in_dim": 128,
+
+    "segment_size": 8960,
+    "code_hop_size": 320,
+    "f0": false,
+    "num_mels": 80,
+    "num_freq": 1025,
+    "n_fft": 1024,
+    "hop_size": 256,
+    "win_size": 1024,
+
+    "dur_prediction_weight": 1.0,
+    "dur_predictor_params": {
+        "encoder_embed_dim": 128,
+        "var_pred_hidden_dim": 128,
+        "var_pred_kernel_size": 3,
+        "var_pred_dropout": 0.5
+    },
+
+    "sampling_rate": 16000,
+
+    "fmin": 0,
+    "fmax": 8000,
+    "fmax_for_loss": null,
+
+    "num_workers": 4,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "env://"
+    }
+}