Upload 9 files

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "vasista22/whisper-kannada-tiny",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "suppress_tokens": [],
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e93abd11010d91a10c570c65411e4c287d8d6b3fa4f964e5c2cc30a3c3a010
+size 151061672

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ca1f17a3908cc9ae7d5a08cdab8ec3771a190694314f4109881739a79dced5
+size 297616186

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3505da080f4dc5a8eea8abd004ed7ce11a56f181ee06d5af2cf5b030dae1d9
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35c47f6a21ee1bb8f2f8642578cb8c19ffdc3fefc7de53d643d321b1980b5e3
+size 1064

trainer_state.json

@@ -0,0 +1,354 @@
+{
+  "best_metric": 24.489795918367346,
+  "best_model_checkpoint": "/content/drive/MyDrive/vavista_kannada_collection_sales_bot_v2/checkpoint-900",
+  "epoch": 14.285714285714286,
+  "eval_steps": 100,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 54.585182189941406,
+      "learning_rate": 3.8e-07,
+      "loss": 2.0199,
+      "step": 25
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 38.83250427246094,
+      "learning_rate": 8.8e-07,
+      "loss": 1.7912,
+      "step": 50
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 33.85667037963867,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 1.2745,
+      "step": 75
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 16.32790184020996,
+      "learning_rate": 1.8800000000000002e-06,
+      "loss": 0.7215,
+      "step": 100
+    },
+    {
+      "epoch": 1.59,
+      "eval_loss": 0.5508027672767639,
+      "eval_runtime": 174.0594,
+      "eval_samples_per_second": 1.419,
+      "eval_steps_per_second": 0.046,
+      "eval_wer": 116.3265306122449,
+      "step": 100
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 9.59360408782959,
+      "learning_rate": 2.38e-06,
+      "loss": 0.4407,
+      "step": 125
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 7.552663326263428,
+      "learning_rate": 2.88e-06,
+      "loss": 0.3329,
+      "step": 150
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 7.011340141296387,
+      "learning_rate": 3.3800000000000007e-06,
+      "loss": 0.2694,
+      "step": 175
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 5.541098117828369,
+      "learning_rate": 3.88e-06,
+      "loss": 0.2487,
+      "step": 200
+    },
+    {
+      "epoch": 3.17,
+      "eval_loss": 0.2373683899641037,
+      "eval_runtime": 132.9698,
+      "eval_samples_per_second": 1.858,
+      "eval_steps_per_second": 0.06,
+      "eval_wer": 71.68367346938776,
+      "step": 200
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 4.505865573883057,
+      "learning_rate": 4.38e-06,
+      "loss": 0.1927,
+      "step": 225
+    },
+    {
+      "epoch": 3.97,
+      "grad_norm": 5.797987461090088,
+      "learning_rate": 4.880000000000001e-06,
+      "loss": 0.1946,
+      "step": 250
+    },
+    {
+      "epoch": 4.37,
+      "grad_norm": 4.06318998336792,
+      "learning_rate": 5.380000000000001e-06,
+      "loss": 0.161,
+      "step": 275
+    },
+    {
+      "epoch": 4.76,
+      "grad_norm": 3.223536252975464,
+      "learning_rate": 5.8800000000000005e-06,
+      "loss": 0.139,
+      "step": 300
+    },
+    {
+      "epoch": 4.76,
+      "eval_loss": 0.18038798868656158,
+      "eval_runtime": 87.9591,
+      "eval_samples_per_second": 2.808,
+      "eval_steps_per_second": 0.091,
+      "eval_wer": 40.05102040816326,
+      "step": 300
+    },
+    {
+      "epoch": 5.16,
+      "grad_norm": 5.675058841705322,
+      "learning_rate": 6.380000000000001e-06,
+      "loss": 0.1185,
+      "step": 325
+    },
+    {
+      "epoch": 5.56,
+      "grad_norm": 3.9274826049804688,
+      "learning_rate": 6.88e-06,
+      "loss": 0.1022,
+      "step": 350
+    },
+    {
+      "epoch": 5.95,
+      "grad_norm": 3.3899903297424316,
+      "learning_rate": 7.3800000000000005e-06,
+      "loss": 0.1012,
+      "step": 375
+    },
+    {
+      "epoch": 6.35,
+      "grad_norm": 2.7243378162384033,
+      "learning_rate": 7.88e-06,
+      "loss": 0.0712,
+      "step": 400
+    },
+    {
+      "epoch": 6.35,
+      "eval_loss": 0.16518759727478027,
+      "eval_runtime": 45.1355,
+      "eval_samples_per_second": 5.472,
+      "eval_steps_per_second": 0.177,
+      "eval_wer": 29.591836734693878,
+      "step": 400
+    },
+    {
+      "epoch": 6.75,
+      "grad_norm": 5.021995544433594,
+      "learning_rate": 8.380000000000001e-06,
+      "loss": 0.0718,
+      "step": 425
+    },
+    {
+      "epoch": 7.14,
+      "grad_norm": 2.2155253887176514,
+      "learning_rate": 8.880000000000001e-06,
+      "loss": 0.0687,
+      "step": 450
+    },
+    {
+      "epoch": 7.54,
+      "grad_norm": 3.375765562057495,
+      "learning_rate": 9.38e-06,
+      "loss": 0.0506,
+      "step": 475
+    },
+    {
+      "epoch": 7.94,
+      "grad_norm": 2.747950553894043,
+      "learning_rate": 9.88e-06,
+      "loss": 0.0448,
+      "step": 500
+    },
+    {
+      "epoch": 7.94,
+      "eval_loss": 0.15877747535705566,
+      "eval_runtime": 45.849,
+      "eval_samples_per_second": 5.387,
+      "eval_steps_per_second": 0.174,
+      "eval_wer": 26.53061224489796,
+      "step": 500
+    },
+    {
+      "epoch": 8.33,
+      "grad_norm": 2.5800018310546875,
+      "learning_rate": 9.620000000000001e-06,
+      "loss": 0.0336,
+      "step": 525
+    },
+    {
+      "epoch": 8.73,
+      "grad_norm": 2.498263359069824,
+      "learning_rate": 9.12e-06,
+      "loss": 0.0264,
+      "step": 550
+    },
+    {
+      "epoch": 9.13,
+      "grad_norm": 1.941878318786621,
+      "learning_rate": 8.62e-06,
+      "loss": 0.0295,
+      "step": 575
+    },
+    {
+      "epoch": 9.52,
+      "grad_norm": 2.1652817726135254,
+      "learning_rate": 8.120000000000002e-06,
+      "loss": 0.0186,
+      "step": 600
+    },
+    {
+      "epoch": 9.52,
+      "eval_loss": 0.17014923691749573,
+      "eval_runtime": 45.3455,
+      "eval_samples_per_second": 5.447,
+      "eval_steps_per_second": 0.176,
+      "eval_wer": 27.29591836734694,
+      "step": 600
+    },
+    {
+      "epoch": 9.92,
+      "grad_norm": 1.3376543521881104,
+      "learning_rate": 7.620000000000001e-06,
+      "loss": 0.02,
+      "step": 625
+    },
+    {
+      "epoch": 10.32,
+      "grad_norm": 1.175929069519043,
+      "learning_rate": 7.1200000000000004e-06,
+      "loss": 0.013,
+      "step": 650
+    },
+    {
+      "epoch": 10.71,
+      "grad_norm": 1.1778250932693481,
+      "learning_rate": 6.620000000000001e-06,
+      "loss": 0.0115,
+      "step": 675
+    },
+    {
+      "epoch": 11.11,
+      "grad_norm": 1.2574666738510132,
+      "learning_rate": 6.120000000000001e-06,
+      "loss": 0.0115,
+      "step": 700
+    },
+    {
+      "epoch": 11.11,
+      "eval_loss": 0.17647403478622437,
+      "eval_runtime": 45.0453,
+      "eval_samples_per_second": 5.483,
+      "eval_steps_per_second": 0.178,
+      "eval_wer": 25.637755102040817,
+      "step": 700
+    },
+    {
+      "epoch": 11.51,
+      "grad_norm": 0.981600284576416,
+      "learning_rate": 5.620000000000001e-06,
+      "loss": 0.0068,
+      "step": 725
+    },
+    {
+      "epoch": 11.9,
+      "grad_norm": 1.208804726600647,
+      "learning_rate": 5.12e-06,
+      "loss": 0.0097,
+      "step": 750
+    },
+    {
+      "epoch": 12.3,
+      "grad_norm": 0.9865374565124512,
+      "learning_rate": 4.620000000000001e-06,
+      "loss": 0.0058,
+      "step": 775
+    },
+    {
+      "epoch": 12.7,
+      "grad_norm": 0.5761059522628784,
+      "learning_rate": 4.12e-06,
+      "loss": 0.0057,
+      "step": 800
+    },
+    {
+      "epoch": 12.7,
+      "eval_loss": 0.1846890151500702,
+      "eval_runtime": 45.0489,
+      "eval_samples_per_second": 5.483,
+      "eval_steps_per_second": 0.178,
+      "eval_wer": 26.27551020408163,
+      "step": 800
+    },
+    {
+      "epoch": 13.1,
+      "grad_norm": 0.34698066115379333,
+      "learning_rate": 3.62e-06,
+      "loss": 0.0049,
+      "step": 825
+    },
+    {
+      "epoch": 13.49,
+      "grad_norm": 0.2580834925174713,
+      "learning_rate": 3.12e-06,
+      "loss": 0.0036,
+      "step": 850
+    },
+    {
+      "epoch": 13.89,
+      "grad_norm": 0.6976760625839233,
+      "learning_rate": 2.6200000000000003e-06,
+      "loss": 0.0043,
+      "step": 875
+    },
+    {
+      "epoch": 14.29,
+      "grad_norm": 0.257933646440506,
+      "learning_rate": 2.12e-06,
+      "loss": 0.0031,
+      "step": 900
+    },
+    {
+      "epoch": 14.29,
+      "eval_loss": 0.18790897727012634,
+      "eval_runtime": 45.02,
+      "eval_samples_per_second": 5.486,
+      "eval_steps_per_second": 0.178,
+      "eval_wer": 24.489795918367346,
+      "step": 900
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 16,
+  "save_steps": 100,
+  "total_flos": 7.0350926118912e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77a39f7cd5157dd63feabbd16fecefb90d3b008a0f6ad2c4681ef69006a8664
+size 5112