Training in progress, step 4000

.gitattributes

@@ -33,3 +33,5 @@ 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
+mnist_test.csv filter=lfs diff=lfs merge=lfs -text
+mnist_train_small.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,19 @@
+This directory includes a few sample datasets to get you started.
+
+*   `california_housing_data*.csv` is California housing data from the 1990 US
+    Census; more information is available at:
+    https://docs.google.com/document/d/e/2PACX-1vRhYtsvc5eOR2FWNCwaBiKL6suIOrxJig8LcSBbmCbyYsayia_DvPOOBlXZ4CAlQ5nlDD8kTaIDRwrN/pub
+
+*   `mnist_*.csv` is a small sample of the
+    [MNIST database](https://en.wikipedia.org/wiki/MNIST_database), which is
+    described at: http://yann.lecun.com/exdb/mnist/
+
+*   `anscombe.json` contains a copy of
+    [Anscombe's quartet](https://en.wikipedia.org/wiki/Anscombe%27s_quartet); it
+    was originally described in
+
+    Anscombe, F. J. (1973). 'Graphs in Statistical Analysis'. American
+    Statistician. 27 (1): 17-21. JSTOR 2682899.
+
+    and our copy was prepared by the
+    [vega_datasets library](https://github.com/altair-viz/vega_datasets/blob/4f67bdaad10f45e3549984e17e1b3088c731503d/vega_datasets/_data/anscombe.json).

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}

anscombe.json

@@ -0,0 +1,49 @@
+[
+  {"Series":"I", "X":10.0, "Y":8.04},
+  {"Series":"I", "X":8.0, "Y":6.95},
+  {"Series":"I", "X":13.0, "Y":7.58},
+  {"Series":"I", "X":9.0, "Y":8.81},
+  {"Series":"I", "X":11.0, "Y":8.33},
+  {"Series":"I", "X":14.0, "Y":9.96},
+  {"Series":"I", "X":6.0, "Y":7.24},
+  {"Series":"I", "X":4.0, "Y":4.26},
+  {"Series":"I", "X":12.0, "Y":10.84},
+  {"Series":"I", "X":7.0, "Y":4.81},
+  {"Series":"I", "X":5.0, "Y":5.68},
+
+  {"Series":"II", "X":10.0, "Y":9.14},
+  {"Series":"II", "X":8.0, "Y":8.14},
+  {"Series":"II", "X":13.0, "Y":8.74},
+  {"Series":"II", "X":9.0, "Y":8.77},
+  {"Series":"II", "X":11.0, "Y":9.26},
+  {"Series":"II", "X":14.0, "Y":8.10},
+  {"Series":"II", "X":6.0, "Y":6.13},
+  {"Series":"II", "X":4.0, "Y":3.10},
+  {"Series":"II", "X":12.0, "Y":9.13},
+  {"Series":"II", "X":7.0, "Y":7.26},
+  {"Series":"II", "X":5.0, "Y":4.74},
+
+  {"Series":"III", "X":10.0, "Y":7.46},
+  {"Series":"III", "X":8.0, "Y":6.77},
+  {"Series":"III", "X":13.0, "Y":12.74},
+  {"Series":"III", "X":9.0, "Y":7.11},
+  {"Series":"III", "X":11.0, "Y":7.81},
+  {"Series":"III", "X":14.0, "Y":8.84},
+  {"Series":"III", "X":6.0, "Y":6.08},
+  {"Series":"III", "X":4.0, "Y":5.39},
+  {"Series":"III", "X":12.0, "Y":8.15},
+  {"Series":"III", "X":7.0, "Y":6.42},
+  {"Series":"III", "X":5.0, "Y":5.73},
+
+  {"Series":"IV", "X":8.0, "Y":6.58},
+  {"Series":"IV", "X":8.0, "Y":5.76},
+  {"Series":"IV", "X":8.0, "Y":7.71},
+  {"Series":"IV", "X":8.0, "Y":8.84},
+  {"Series":"IV", "X":8.0, "Y":8.47},
+  {"Series":"IV", "X":8.0, "Y":7.04},
+  {"Series":"IV", "X":8.0, "Y":5.25},
+  {"Series":"IV", "X":19.0, "Y":12.50},
+  {"Series":"IV", "X":8.0, "Y":5.56},
+  {"Series":"IV", "X":8.0, "Y":7.91},
+  {"Series":"IV", "X":8.0, "Y":6.89}
+]

config.json

@@ -0,0 +1,91 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForTextToSpeech"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_speech_positions": 1876,
+  "max_text_positions": 600,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

mnist_test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c292478d94ec3a01461bdfa82eb0885d262eb09e615679b2d69dedb6ad09e7
+size 18289443

mnist_train_small.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef64781aa03180f4f5ce504314f058f5d0227277df86060473d973cf43b033e
+size 36523880

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ef92b7fd7d6d36eccfb499efb90f153a67c72297e378d7fd8ba06f4eab27bf
+size 577789320

runs/Apr22_12-08-18_4e15c3e30aa5/events.out.tfevents.1745323712.4e15c3e30aa5.390.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70331eab4161009db1c272f5c906499edcc2aef2a31646604ba7a83ef56f009b
+size 41717

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spm_char.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 600,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "processor_class": "SpeechT5Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SpeechT5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a07297637dcfcbb27d215e8237e29698629016064606149fb94501e13fefdfe
+size 5432