End of training

README.md

@@ -1,102 +1,59 @@
 ---
-datasets:
-- DataLabX/ScreenTalk-XS
+library_name: peft
 language:
 - en
 license: apache-2.0
-metrics:
-- wer
-base_model:
-- openai/whisper-small
+base_model: openai/whisper-small
+tags:
+- hf-asr-leaderboard
+- generated_from_trainer
+datasets:
+- DataLabX/ScreenTalk-XS
+model-index:
+- name: ScreenTalk-xs
+  results: []
 ---
 
-# **ScreenTalk**
-**Fine-tuned version of `openai/whisper-small` on the `DataLabX/ScreenTalk-XS` dataset**
-
-## **Model Summary**
-ScreenTalk is a fine-tuned version of OpenAI's Whisper-Small model, specifically trained for speech-to-text transcription using the **DataLabX/ScreenTalk-XS** dataset. The model is optimized to improve automatic speech recognition (ASR) performance in its target domain.
-
-On the evaluation set, it achieves:
-- **Loss**: `0.375`
-- **Word Error Rate (WER)**: `21.27%`
-
-## **Intended Uses & Limitations**
-### **Intended Use Cases**
-- **Speech-to-text transcription** for audio in the domain covered by `ScreenTalk-XS`
-- **Automatic subtitling** and **audio content analysis**
-- **Voice-assisted applications** where accurate ASR is needed
-
-### **Limitations**
-- May not generalize well to **out-of-domain** data
-- Performance is dependent on **audio quality** and **background noise**
-- The model is optimized for English (or the target language in `ScreenTalk-XS`)
-
-## **Training and Evaluation Data**
-The model was fine-tuned on the `DataLabX/ScreenTalk-XS` dataset, which contains domain-specific speech recordings. The dataset has been preprocessed and formatted to enhance ASR capabilities in specific contexts.
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-## **Training Procedure**
-### **Hyperparameters**
-The model was trained with the following hyperparameters:
+# ScreenTalk-xs
 
-| Hyperparameter                | Value        |
-|--------------------------------|-------------|
-| Learning Rate                  | `5e-05`     |
-| Train Batch Size               | `8`         |
-| Eval Batch Size                | `8`         |
-| Seed                            | `42`        |
-| Gradient Accumulation Steps     | `8`         |
-| Total Train Batch Size          | `64`        |
-| Optimizer                       | `AdamW` (β1=0.9, β2=0.999, ε=1e-08) |
-| Learning Rate Scheduler         | `Linear`    |
-| Warmup Steps                    | `10`        |
-| Total Training Steps            | `200`       |
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the DataLabX/ScreenTalk-XS dataset.
 
-### **Training Progress**
-The model was trained for **200 steps**, and the WER improved over time:
+## Model description
 
-| Step | Training Loss | Validation Loss | WER (%) |
-|------|--------------|----------------|---------|
-| 20   | 1.1515       | 1.0011         | 22.33   |
-| 40   | 0.7024       | 0.6125         | 26.64   |
-| 60   | 0.3648       | 0.4175         | 23.00   |
-| 80   | 0.3753       | 0.3991         | 22.09   |
-| 100  | 0.3838       | 0.3952         | 22.83   |
-| 120  | 0.3358       | 0.3834         | 22.59   |
-| 140  | 0.1462       | 0.3924         | 22.01   |
-| 160  | 0.1636       | 0.3847         | 21.50   |
-| 180  | 0.1587       | 0.3778         | 21.36   |
-| 200  | 0.1583       | 0.3759         | 21.27   |
+More information needed
 
-## **Framework Versions**
-- **PEFT**: `0.14.0`
-- **Transformers**: `4.48.3`
-- **PyTorch**: `2.5.1+cu124`
-- **Datasets**: `3.3.2`
-- **Tokenizers**: `0.21.0`
+## Intended uses & limitations
 
-## **How to Use**
-To load and use this model for inference:
+More information needed
 
-```python
-from transformers import pipeline
+## Training and evaluation data
 
-asr_pipeline = pipeline("automatic-speech-recognition", model="fj11/ScreenTalk-xs")
-audio_file = "path/to/audio.wav"
+More information needed
 
-transcription = asr_pipeline(audio_file)
-print(transcription["text"])
-```
+## Training procedure
 
-## **Citation**
-If you use this model, please cite:
+### Training hyperparameters
 
-```java
-@misc{ScreenTalk-xs,
-  title={ScreenTalk: A Fine-tuned Whisper-Small Model for Speech Recognition},
-  author={Your Name or Organization},
-  year={2025},
-  url={https://huggingface.co/fj11/ScreenTalk-xs}
-}
-```
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- training_steps: 5700
+- mixed_precision_training: Native AMP
 
+### Framework versions
 
+- PEFT 0.14.0
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-small",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "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 sha256:726028606b861d502b0807e0611a0ed77905f5a1e69edcfb1f5a4416b2697269
+size 14176064

runs/Mar08_01-33-44_9c4eb6e5c5b2/events.out.tfevents.1741397628.9c4eb6e5c5b2.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186373ba88aa74b25eeb5928124a19b829ba62e42a9cd76acb0c3109049c5b63
+size 19334

runs/Mar08_01-39-29_9c4eb6e5c5b2/events.out.tfevents.1741397972.9c4eb6e5c5b2.31.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e904a20b233e74733b82d4b34dc2bd2064e65212e50de656885241f197c1333b
+size 6809

runs/Mar08_01-40-19_9c4eb6e5c5b2/events.out.tfevents.1741398023.9c4eb6e5c5b2.31.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f373acfa11124692a64f35253c7f046cfaf6d1b35882c7310c388b118607e171
+size 14256

runs/Mar08_01-43-13_9c4eb6e5c5b2/events.out.tfevents.1741398201.9c4eb6e5c5b2.31.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe64bf2536de8da459d54fdfe4e80dabee46c0d2a8e6f19bbb5d72a719752c8
+size 5876

runs/Mar08_01-44-56_9c4eb6e5c5b2/events.out.tfevents.1741398301.9c4eb6e5c5b2.31.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d75bb99a62bd5407c556dbe10823ad8b5d5a06e336c64a0ecb154b845f76f4
+size 13323

runs/Mar08_01-48-20_9c4eb6e5c5b2/events.out.tfevents.1741398503.9c4eb6e5c5b2.31.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18431f07ba1bae4c69b985953411815cccc76fbab28ed45733438817666d947c
+size 5876

runs/Mar08_01-49-07_9c4eb6e5c5b2/events.out.tfevents.1741398551.9c4eb6e5c5b2.31.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a710e4f527f1763a76d9d56b04213ee401d439d7b432a750eabdd8657b5d3c
+size 8780

runs/Mar08_01-51-23_9c4eb6e5c5b2/events.out.tfevents.1741398686.9c4eb6e5c5b2.31.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e9a8d76a3de261f0a7b4e83f4278071cbec74174ff95e017e2b237b0c9dc54e
+size 7016

runs/Mar08_01-55-52_9c4eb6e5c5b2/events.out.tfevents.1741398956.9c4eb6e5c5b2.31.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a498dcb976065059978a94cb0ad1670381ef8a0c5c9e172fbddf9a0085603c63
+size 6290

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff489e9a35fdcdc3c7dedc4059cd48b01358bbdd11c4e90fd449571bff5ce21
+oid sha256:960e2e96a599f9957d3a8376346f9f010edb3fe5f7e6006b846acd86cc2dab9f
 size 5496