Upload 9 files

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+base_model: openai/whisper-large-v3-turbo
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-large-v3-turbo",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "out_proj",
+    "k_proj",
+    "v_proj",
+    "fc1",
+    "fc2",
+    "q_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefe5d9fa874c63f8329babb29a4e8559cdf8d2c4a904374cec4815cc5193e31
+size 55769968

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "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:db2d34466ecc8adaffb67b45544cb286c12878c24c4c4a87b824bfa468d9a58b
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33fac0ac2e2f1ca60f2c7f8ea17bd1b7a9848ffaa27ee9bad6d798193152f6ad
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d773ede923ab49b4fc31da4327484020e7ea57f0b25b6d2968050e18bdb05a43
+size 1064

trainer_state.json

@@ -0,0 +1,482 @@
+{
+  "best_metric": 44.631731967326594,
+  "best_model_checkpoint": "./whisper-large-v3-turbo-ar/checkpoint-1725",
+  "epoch": 4.986975397973951,
+  "eval_steps": 500,
+  "global_step": 1725,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08683068017366136,
+      "grad_norm": 2.354785919189453,
+      "learning_rate": 2.9513043478260868e-05,
+      "loss": 1.1449,
+      "step": 30
+    },
+    {
+      "epoch": 0.1736613603473227,
+      "grad_norm": 2.7719461917877197,
+      "learning_rate": 2.8991304347826086e-05,
+      "loss": 0.7766,
+      "step": 60
+    },
+    {
+      "epoch": 0.26049204052098407,
+      "grad_norm": 2.36008358001709,
+      "learning_rate": 2.8469565217391304e-05,
+      "loss": 0.6757,
+      "step": 90
+    },
+    {
+      "epoch": 0.3473227206946454,
+      "grad_norm": 2.6321663856506348,
+      "learning_rate": 2.7947826086956522e-05,
+      "loss": 0.6358,
+      "step": 120
+    },
+    {
+      "epoch": 0.4341534008683068,
+      "grad_norm": 2.7725794315338135,
+      "learning_rate": 2.742608695652174e-05,
+      "loss": 0.6335,
+      "step": 150
+    },
+    {
+      "epoch": 0.5209840810419681,
+      "grad_norm": 2.8601250648498535,
+      "learning_rate": 2.690434782608696e-05,
+      "loss": 0.5739,
+      "step": 180
+    },
+    {
+      "epoch": 0.6078147612156295,
+      "grad_norm": 2.6586220264434814,
+      "learning_rate": 2.6382608695652173e-05,
+      "loss": 0.5879,
+      "step": 210
+    },
+    {
+      "epoch": 0.6946454413892909,
+      "grad_norm": 2.727559804916382,
+      "learning_rate": 2.587826086956522e-05,
+      "loss": 0.5544,
+      "step": 240
+    },
+    {
+      "epoch": 0.7814761215629522,
+      "grad_norm": 2.643286943435669,
+      "learning_rate": 2.5356521739130434e-05,
+      "loss": 0.5632,
+      "step": 270
+    },
+    {
+      "epoch": 0.8683068017366136,
+      "grad_norm": 4.257571697235107,
+      "learning_rate": 2.4834782608695652e-05,
+      "loss": 0.5424,
+      "step": 300
+    },
+    {
+      "epoch": 0.9551374819102749,
+      "grad_norm": 2.859233856201172,
+      "learning_rate": 2.431304347826087e-05,
+      "loss": 0.5055,
+      "step": 330
+    },
+    {
+      "epoch": 1.0,
+      "eval_cer": 23.096209332404737,
+      "eval_loss": 0.35870930552482605,
+      "eval_runtime": 454.9155,
+      "eval_samples_per_second": 6.071,
+      "eval_steps_per_second": 0.38,
+      "eval_wer": 50.66108265263741,
+      "step": 346
+    },
+    {
+      "epoch": 1.0405209840810419,
+      "grad_norm": 2.8805744647979736,
+      "learning_rate": 2.3808695652173917e-05,
+      "loss": 0.5452,
+      "step": 360
+    },
+    {
+      "epoch": 1.1273516642547032,
+      "grad_norm": 2.1588120460510254,
+      "learning_rate": 2.328695652173913e-05,
+      "loss": 0.4843,
+      "step": 390
+    },
+    {
+      "epoch": 1.2141823444283646,
+      "grad_norm": 3.3963794708251953,
+      "learning_rate": 2.276521739130435e-05,
+      "loss": 0.4844,
+      "step": 420
+    },
+    {
+      "epoch": 1.301013024602026,
+      "grad_norm": 3.632931709289551,
+      "learning_rate": 2.2243478260869567e-05,
+      "loss": 0.4702,
+      "step": 450
+    },
+    {
+      "epoch": 1.3878437047756873,
+      "grad_norm": 2.5184545516967773,
+      "learning_rate": 2.1721739130434782e-05,
+      "loss": 0.4683,
+      "step": 480
+    },
+    {
+      "epoch": 1.4746743849493487,
+      "grad_norm": 2.705561876296997,
+      "learning_rate": 2.12e-05,
+      "loss": 0.4566,
+      "step": 510
+    },
+    {
+      "epoch": 1.56150506512301,
+      "grad_norm": 2.8649938106536865,
+      "learning_rate": 2.067826086956522e-05,
+      "loss": 0.4417,
+      "step": 540
+    },
+    {
+      "epoch": 1.6483357452966714,
+      "grad_norm": 2.338636875152588,
+      "learning_rate": 2.0156521739130433e-05,
+      "loss": 0.4768,
+      "step": 570
+    },
+    {
+      "epoch": 1.7351664254703327,
+      "grad_norm": 2.246873617172241,
+      "learning_rate": 1.963478260869565e-05,
+      "loss": 0.4525,
+      "step": 600
+    },
+    {
+      "epoch": 1.821997105643994,
+      "grad_norm": 2.4678239822387695,
+      "learning_rate": 1.911304347826087e-05,
+      "loss": 0.4335,
+      "step": 630
+    },
+    {
+      "epoch": 1.9088277858176554,
+      "grad_norm": 2.090752363204956,
+      "learning_rate": 1.8591304347826084e-05,
+      "loss": 0.4545,
+      "step": 660
+    },
+    {
+      "epoch": 1.9956584659913168,
+      "grad_norm": 3.091327428817749,
+      "learning_rate": 1.8069565217391306e-05,
+      "loss": 0.4009,
+      "step": 690
+    },
+    {
+      "epoch": 2.0,
+      "eval_cer": 21.8498988492024,
+      "eval_loss": 0.3138186037540436,
+      "eval_runtime": 453.4358,
+      "eval_samples_per_second": 6.091,
+      "eval_steps_per_second": 0.382,
+      "eval_wer": 47.57372282984909,
+      "step": 692
+    },
+    {
+      "epoch": 2.0810419681620838,
+      "grad_norm": 2.364564895629883,
+      "learning_rate": 1.7547826086956524e-05,
+      "loss": 0.4023,
+      "step": 720
+    },
+    {
+      "epoch": 2.167872648335745,
+      "grad_norm": 2.765427827835083,
+      "learning_rate": 1.7026086956521742e-05,
+      "loss": 0.4107,
+      "step": 750
+    },
+    {
+      "epoch": 2.2547033285094065,
+      "grad_norm": 3.069685220718384,
+      "learning_rate": 1.6504347826086957e-05,
+      "loss": 0.3823,
+      "step": 780
+    },
+    {
+      "epoch": 2.341534008683068,
+      "grad_norm": 2.4570705890655518,
+      "learning_rate": 1.5982608695652175e-05,
+      "loss": 0.4213,
+      "step": 810
+    },
+    {
+      "epoch": 2.428364688856729,
+      "grad_norm": 2.609337091445923,
+      "learning_rate": 1.5460869565217393e-05,
+      "loss": 0.4028,
+      "step": 840
+    },
+    {
+      "epoch": 2.5151953690303905,
+      "grad_norm": 3.4422805309295654,
+      "learning_rate": 1.493913043478261e-05,
+      "loss": 0.4045,
+      "step": 870
+    },
+    {
+      "epoch": 2.602026049204052,
+      "grad_norm": 2.808845043182373,
+      "learning_rate": 1.4417391304347827e-05,
+      "loss": 0.4044,
+      "step": 900
+    },
+    {
+      "epoch": 2.6888567293777133,
+      "grad_norm": 2.957320213317871,
+      "learning_rate": 1.3895652173913044e-05,
+      "loss": 0.4084,
+      "step": 930
+    },
+    {
+      "epoch": 2.7756874095513746,
+      "grad_norm": 3.7300264835357666,
+      "learning_rate": 1.3373913043478262e-05,
+      "loss": 0.4087,
+      "step": 960
+    },
+    {
+      "epoch": 2.862518089725036,
+      "grad_norm": 3.3813674449920654,
+      "learning_rate": 1.2852173913043478e-05,
+      "loss": 0.3932,
+      "step": 990
+    },
+    {
+      "epoch": 2.9493487698986973,
+      "grad_norm": 2.602900505065918,
+      "learning_rate": 1.2330434782608695e-05,
+      "loss": 0.3745,
+      "step": 1020
+    },
+    {
+      "epoch": 3.0,
+      "eval_cer": 20.94783271979571,
+      "eval_loss": 0.2958418130874634,
+      "eval_runtime": 455.4865,
+      "eval_samples_per_second": 6.064,
+      "eval_steps_per_second": 0.38,
+      "eval_wer": 45.43126124878859,
+      "step": 1038
+    },
+    {
+      "epoch": 3.0347322720694647,
+      "grad_norm": 2.719440221786499,
+      "learning_rate": 1.1808695652173913e-05,
+      "loss": 0.4,
+      "step": 1050
+    },
+    {
+      "epoch": 3.121562952243126,
+      "grad_norm": 2.4568002223968506,
+      "learning_rate": 1.1286956521739131e-05,
+      "loss": 0.3715,
+      "step": 1080
+    },
+    {
+      "epoch": 3.2083936324167874,
+      "grad_norm": 3.5121898651123047,
+      "learning_rate": 1.0765217391304349e-05,
+      "loss": 0.3608,
+      "step": 1110
+    },
+    {
+      "epoch": 3.295224312590449,
+      "grad_norm": 3.059799909591675,
+      "learning_rate": 1.0243478260869565e-05,
+      "loss": 0.3674,
+      "step": 1140
+    },
+    {
+      "epoch": 3.38205499276411,
+      "grad_norm": 3.2511227130889893,
+      "learning_rate": 9.721739130434782e-06,
+      "loss": 0.3505,
+      "step": 1170
+    },
+    {
+      "epoch": 3.4688856729377715,
+      "grad_norm": 2.990471124649048,
+      "learning_rate": 9.2e-06,
+      "loss": 0.3435,
+      "step": 1200
+    },
+    {
+      "epoch": 3.555716353111433,
+      "grad_norm": 3.523132562637329,
+      "learning_rate": 8.678260869565218e-06,
+      "loss": 0.3812,
+      "step": 1230
+    },
+    {
+      "epoch": 3.642547033285094,
+      "grad_norm": 3.101360559463501,
+      "learning_rate": 8.156521739130435e-06,
+      "loss": 0.3641,
+      "step": 1260
+    },
+    {
+      "epoch": 3.7293777134587556,
+      "grad_norm": 2.8961117267608643,
+      "learning_rate": 7.634782608695653e-06,
+      "loss": 0.3278,
+      "step": 1290
+    },
+    {
+      "epoch": 3.816208393632417,
+      "grad_norm": 2.8601419925689697,
+      "learning_rate": 7.113043478260869e-06,
+      "loss": 0.3772,
+      "step": 1320
+    },
+    {
+      "epoch": 3.9030390738060783,
+      "grad_norm": 3.368321657180786,
+      "learning_rate": 6.591304347826087e-06,
+      "loss": 0.4056,
+      "step": 1350
+    },
+    {
+      "epoch": 3.9898697539797396,
+      "grad_norm": 2.85530686378479,
+      "learning_rate": 6.0695652173913045e-06,
+      "loss": 0.3858,
+      "step": 1380
+    },
+    {
+      "epoch": 4.0,
+      "eval_cer": 21.01416111166385,
+      "eval_loss": 0.2913440763950348,
+      "eval_runtime": 453.8291,
+      "eval_samples_per_second": 6.086,
+      "eval_steps_per_second": 0.381,
+      "eval_wer": 44.991693202270525,
+      "step": 1384
+    },
+    {
+      "epoch": 4.075253256150506,
+      "grad_norm": 3.0076441764831543,
+      "learning_rate": 5.5478260869565226e-06,
+      "loss": 0.3231,
+      "step": 1410
+    },
+    {
+      "epoch": 4.1620839363241675,
+      "grad_norm": 2.4868621826171875,
+      "learning_rate": 5.026086956521739e-06,
+      "loss": 0.3619,
+      "step": 1440
+    },
+    {
+      "epoch": 4.248914616497829,
+      "grad_norm": 2.356128215789795,
+      "learning_rate": 4.504347826086956e-06,
+      "loss": 0.3499,
+      "step": 1470
+    },
+    {
+      "epoch": 4.33574529667149,
+      "grad_norm": 2.7863681316375732,
+      "learning_rate": 3.982608695652174e-06,
+      "loss": 0.3474,
+      "step": 1500
+    },
+    {
+      "epoch": 4.422575976845152,
+      "grad_norm": 2.680084228515625,
+      "learning_rate": 3.4608695652173912e-06,
+      "loss": 0.3297,
+      "step": 1530
+    },
+    {
+      "epoch": 4.509406657018813,
+      "grad_norm": 3.3411145210266113,
+      "learning_rate": 2.939130434782609e-06,
+      "loss": 0.3275,
+      "step": 1560
+    },
+    {
+      "epoch": 4.596237337192474,
+      "grad_norm": 3.159189224243164,
+      "learning_rate": 2.417391304347826e-06,
+      "loss": 0.3385,
+      "step": 1590
+    },
+    {
+      "epoch": 4.683068017366136,
+      "grad_norm": 3.1586883068084717,
+      "learning_rate": 1.8956521739130434e-06,
+      "loss": 0.3406,
+      "step": 1620
+    },
+    {
+      "epoch": 4.769898697539798,
+      "grad_norm": 3.2731616497039795,
+      "learning_rate": 1.373913043478261e-06,
+      "loss": 0.3344,
+      "step": 1650
+    },
+    {
+      "epoch": 4.856729377713458,
+      "grad_norm": 3.3731155395507812,
+      "learning_rate": 8.521739130434783e-07,
+      "loss": 0.3505,
+      "step": 1680
+    },
+    {
+      "epoch": 4.943560057887121,
+      "grad_norm": 2.6627700328826904,
+      "learning_rate": 3.304347826086957e-07,
+      "loss": 0.3537,
+      "step": 1710
+    },
+    {
+      "epoch": 4.986975397973951,
+      "eval_cer": 20.71899976785063,
+      "eval_loss": 0.2904263138771057,
+      "eval_runtime": 454.269,
+      "eval_samples_per_second": 6.08,
+      "eval_steps_per_second": 0.381,
+      "eval_wer": 44.631731967326594,
+      "step": 1725
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 1725,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.569687426039808e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bca1d0c5915f04b494ef619855bd516a494e401d2ec340a41f92e2197195d3
+size 5432