Add model, Gradio demo, and README

BATSH.sh

@@ -0,0 +1,18 @@
+huggingface-cli login 
+transformers-cli repo create mms-darija-finetuned --organization your-org  # if needed
+
+cd mms-darija-finetuned
+cp -r output_dir/* .  # copier tout le modèle fine-tuné
+cp ../README.md .
+cp ../app.py .
+git add .
+git commit -m "Upload Darija fine-tuned MMS model + Space demo"
+git push
+cd mms-darija-finetuned
+git init
+git lfs install
+git remote add orig
+in https://huggingface.co/YOUR_USERNAME/mms-darija-finetuned
+git add .
+git commit -m "Upload fine-tuned Darija MMS model"
+git push -u origin master

PUSH.PY

@@ -0,0 +1,204 @@
+#!/usr/bin/env python3
+"""
+Complete script to push model, demo, and README to HuggingFace Hub
+"""
+
+import os
+from huggingface_hub import HfApi
+
+# Configuration
+REPO_ID = "HAMMALE/mms-darija-finetuned"
+MODEL_DIR = "./mms-darija-finetuned"
+
+# Initialize API
+api = HfApi()
+
+# Create repository
+print("📦 Creating repository...")
+api.create_repo(
+    repo_id=REPO_ID,
+    repo_type="model",
+    exist_ok=True
+)
+
+# Create README.md
+readme_content = """---
+language:
+- ar
+- ary
+tags:
+- speech-recognition
+- audio
+- wav2vec2
+- mms
+- darija
+- moroccan-arabic
+- bible
+license: apache-2.0
+datasets:
+- atlasia/darija_bible_aligned
+metrics:
+- wer
+widget:
+- example_title: "Darija Speech Example"
+  src: "https://example.com/darija_sample.wav"
+---
+
+# MMS-1B-All Fine-tuned on Darija Bible Dataset
+
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the [atlasia/darija_bible_aligned](https://huggingface.co/datasets/atlasia/darija_bible_aligned) dataset for Moroccan Arabic (Darija) speech recognition.
+
+## Model Description
+
+- **Model type:** Speech Recognition (CTC)
+- **Language:** Moroccan Arabic (Darija)
+- **Base model:** facebook/mms-1b-all
+- **Dataset:** Darija Bible Aligned Dataset
+- **License:** Apache 2.0
+
+## Usage
+
+```python
+from transformers import AutoProcessor, AutoModelForCTC
+import torch
+import librosa
+
+# Load model and processor
+processor = AutoProcessor.from_pretrained("HAMMALE/mms-darija-finetuned")
+model = AutoModelForCTC.from_pretrained("HAMMALE/mms-darija-finetuned")
+
+# Load and preprocess audio
+audio, sr = librosa.load("path/to/darija/audio.wav", sr=16000)
+inputs = processor(audio, sampling_rate=16000, return_tensors="pt")
+
+# Inference
+with torch.no_grad():
+    logits = model(**inputs).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+transcription = processor.batch_decode(predicted_ids)[0]
+print(f"Transcription: {transcription}")
+```
+
+## Training Details
+
+The model was fine-tuned on the Darija Bible Aligned Dataset, which contains audio segments from the Moroccan Standard Translation (MSTD) of the Bible with aligned text transcriptions.
+
+## Limitations
+
+- Trained specifically on religious text (Bible translations)
+- May not perform well on colloquial/everyday Darija speech
+- Limited vocabulary outside religious domain
+
+## Citation
+
+```bibtex
+@misc{darija-mms-finetuned,
+    title={MMS-1B-All Fine-tuned on Darija Bible Dataset},
+    author={HAMMALE},
+    year={2025},
+    publisher={Hugging Face},
+    journal={Hugging Face Model Hub},
+    howpublished={\\url{https://huggingface.co/HAMMALE/mms-darija-finetuned}}
+}
+```
+
+## Acknowledgments
+
+- Original MMS model by Meta AI
+- Darija Bible dataset by Morocco Bible Society
+- Audio alignment using Facebook's MMS toolkit
+"""
+
+# Create app.py for Gradio demo
+app_content = """import gradio as gr
+import torch
+import librosa
+import numpy as np
+from transformers import AutoProcessor, AutoModelForCTC
+
+# Load model and processor
+print("Loading model...")
+processor = AutoProcessor.from_pretrained("HAMMALE/mms-darija-finetuned")
+model = AutoModelForCTC.from_pretrained("HAMMALE/mms-darija-finetuned")
+
+def transcribe_audio(audio_file):
+    try:
+        # Load audio
+        if audio_file is None:
+            return "Please upload an audio file."
+        
+        # Load and preprocess audio
+        audio, sr = librosa.load(audio_file, sr=16000)
+        
+        # Handle very short audio
+        if len(audio) < 1600:  # Less than 0.1 seconds
+            return "Audio too short. Please upload a longer audio file."
+        
+        # Process with model
+        inputs = processor(audio, sampling_rate=16000, return_tensors="pt")
+        
+        # Inference
+        with torch.no_grad():
+            logits = model(**inputs).logits
+        
+        predicted_ids = torch.argmax(logits, dim=-1)
+        transcription = processor.batch_decode(predicted_ids)[0]
+        
+        return transcription if transcription.strip() else "No transcription generated."
+        
+    except Exception as e:
+        return f"Error processing audio: {str(e)}"
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=transcribe_audio,
+    inputs=gr.Audio(type="filepath", label="Upload Darija Audio"),
+    outputs=gr.Textbox(label="Transcription", placeholder="Transcription will appear here..."),
+    title="🎤 Darija Speech Recognition",
+    description="Upload an audio file in Moroccan Arabic (Darija) and get the transcription. This model was fine-tuned on the Darija Bible dataset.",
+    article="Model: [HAMMALE/mms-darija-finetuned](https://huggingface.co/HAMMALE/mms-darija-finetuned)",
+    examples=[
+        # You can add example audio files here if you have them
+    ],
+    cache_examples=False,
+    theme=gr.themes.Soft()
+)
+
+if __name__ == "__main__":
+    demo.launch()
+"""
+
+# Create requirements.txt
+requirements_content = """torch
+transformers
+librosa
+gradio
+numpy
+"""
+
+# Save files to model directory
+print("📝 Creating files...")
+os.makedirs(MODEL_DIR, exist_ok=True)
+
+with open(f"{MODEL_DIR}/README.md", "w", encoding="utf-8") as f:
+    f.write(readme_content)
+
+with open(f"{MODEL_DIR}/app.py", "w", encoding="utf-8") as f:
+    f.write(app_content)
+
+with open(f"{MODEL_DIR}/requirements.txt", "w", encoding="utf-8") as f:
+    f.write(requirements_content)
+
+# Upload entire directory
+print("🚀 Uploading to HuggingFace Hub...")
+api.upload_folder(
+    folder_path=MODEL_DIR,
+    repo_id=REPO_ID,
+    repo_type="model",
+    commit_message="Add model, Gradio demo, and README"
+)
+
+print(f"✅ Complete model pushed to: https://huggingface.co/{REPO_ID}")
+print(f"🎯 Demo available at: https://huggingface.co/spaces/{REPO_ID}")
+print("📱 The Gradio demo will be automatically deployed!")

README.md

@@ -1,199 +1,86 @@
 ---
-library_name: transformers
-tags: []
+language:
+- ar
+- ary
+tags:
+- speech-recognition
+- audio
+- wav2vec2
+- mms
+- darija
+- moroccan-arabic
+- bible
+license: apache-2.0
+datasets:
+- atlasia/darija_bible_aligned
+metrics:
+- wer
+widget:
+- example_title: "Darija Speech Example"
+  src: "https://example.com/darija_sample.wav"
 ---
 
-# Model Card for Model ID
+# MMS-1B-All Fine-tuned on Darija Bible Dataset
 
-<!-- Provide a quick summary of what the model is/does. -->
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the [atlasia/darija_bible_aligned](https://huggingface.co/datasets/atlasia/darija_bible_aligned) dataset for Moroccan Arabic (Darija) speech recognition.
 
+## Model Description
 
+- **Model type:** Speech Recognition (CTC)
+- **Language:** Moroccan Arabic (Darija)
+- **Base model:** facebook/mms-1b-all
+- **Dataset:** Darija Bible Aligned Dataset
+- **License:** Apache 2.0
 
-## Model Details
+## Usage
 
-### Model Description
+```python
+from transformers import AutoProcessor, AutoModelForCTC
+import torch
+import librosa
 
-<!-- Provide a longer summary of what this model is. -->
+# Load model and processor
+processor = AutoProcessor.from_pretrained("HAMMALE/mms-darija-finetuned")
+model = AutoModelForCTC.from_pretrained("HAMMALE/mms-darija-finetuned")
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+# Load and preprocess audio
+audio, sr = librosa.load("path/to/darija/audio.wav", sr=16000)
+inputs = processor(audio, sampling_rate=16000, return_tensors="pt")
 
-- **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]
+# Inference
+with torch.no_grad():
+    logits = model(**inputs).logits
 
-### 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]
+predicted_ids = torch.argmax(logits, dim=-1)
+transcription = processor.batch_decode(predicted_ids)[0]
+print(f"Transcription: {transcription}")
+```
 
 ## 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]
+The model was fine-tuned on the Darija Bible Aligned Dataset, which contains audio segments from the Moroccan Standard Translation (MSTD) of the Bible with aligned text transcriptions.
 
-## More Information [optional]
+## Limitations
 
-[More Information Needed]
+- Trained specifically on religious text (Bible translations)
+- May not perform well on colloquial/everyday Darija speech
+- Limited vocabulary outside religious domain
 
-## Model Card Authors [optional]
+## Citation
 
-[More Information Needed]
+```bibtex
+@misc{darija-mms-finetuned,
+    title={MMS-1B-All Fine-tuned on Darija Bible Dataset},
+    author={HAMMALE},
+    year={2025},
+    publisher={Hugging Face},
+    journal={Hugging Face Model Hub},
+    howpublished={\url{https://huggingface.co/HAMMALE/mms-darija-finetuned}}
+}
+```
 
-## Model Card Contact
+## Acknowledgments
 
-[More Information Needed]
+- Original MMS model by Meta AI
+- Darija Bible dataset by Morocco Bible Society
+- Audio alignment using Facebook's MMS toolkit

Readme.md

@@ -0,0 +1,39 @@
+# MMS-1B-All fine-tuned on Darija Bible Aligned Dataset 
+
+This model is a fine-tuned version of `facebook/mms-1b-all` for Moroccan Arabic (Darija) speech recognition, trained on the **Darija Bible Aligned Dataset** provided by [AtlasAI](https://huggingface.co/atlasia).
+
+## 📊 Dataset
+- **Name**: `atlasia/darija_bible_aligned`
+- **Domain**: Religious texts (Moroccan Darija audio ↔ Arabic text)
+- **License**: See original dataset page.
+
+## 🎯 Intended use
+This model is intended for research and experimentation in low-resource Arabic dialect ASR.
+
+## 🚀 Training Details
+- Base model: `facebook/mms-1b-all`
+- Language: `ara` (Moroccan Arabic)
+- Framework: `Transformers` + `datasets`
+- WER on eval set: *To be filled after training*
+
+## 🙏 Acknowledgements
+Special thanks to **AtlasAI** for providing the aligned Darija Bible dataset.
+
+## 🧪 Demo
+Try the model on your own audio! Check out the demo in the Space or use this snippet:
+
+```python
+from transformers import AutoProcessor, AutoModelForCTC
+import torchaudio
+
+processor = AutoProcessor.from_pretrained("your-username/mms-darija-finetuned")
+model = AutoModelForCTC.from_pretrained("your-username/mms-darija-finetuned")
+
+waveform, sr = torchaudio.load("your_audio.wav")
+inputs = processor(waveform.squeeze().numpy(), sampling_rate=sr, return_tensors="pt")
+with torch.no_grad():
+    logits = model(**inputs).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+transcription = processor.batch_decode(predicted_ids)[0]
+print(transcription)

app.py

@@ -0,0 +1,56 @@
+import gradio as gr
+import torch
+import librosa
+import numpy as np
+from transformers import AutoProcessor, AutoModelForCTC
+
+# Load model and processor
+print("Loading model...")
+processor = AutoProcessor.from_pretrained("HAMMALE/mms-darija-finetuned")
+model = AutoModelForCTC.from_pretrained("HAMMALE/mms-darija-finetuned")
+
+def transcribe_audio(audio_file):
+    try:
+        # Load audio
+        if audio_file is None:
+            return "Please upload an audio file."
+        
+        # Load and preprocess audio
+        audio, sr = librosa.load(audio_file, sr=16000)
+        
+        # Handle very short audio
+        if len(audio) < 1600:  # Less than 0.1 seconds
+            return "Audio too short. Please upload a longer audio file."
+        
+        # Process with model
+        inputs = processor(audio, sampling_rate=16000, return_tensors="pt")
+        
+        # Inference
+        with torch.no_grad():
+            logits = model(**inputs).logits
+        
+        predicted_ids = torch.argmax(logits, dim=-1)
+        transcription = processor.batch_decode(predicted_ids)[0]
+        
+        return transcription if transcription.strip() else "No transcription generated."
+        
+    except Exception as e:
+        return f"Error processing audio: {str(e)}"
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=transcribe_audio,
+    inputs=gr.Audio(type="filepath", label="Upload Darija Audio"),
+    outputs=gr.Textbox(label="Transcription", placeholder="Transcription will appear here..."),
+    title="🎤 Darija Speech Recognition",
+    description="Upload an audio file in Moroccan Arabic (Darija) and get the transcription. This model was fine-tuned on the Darija Bible dataset.",
+    article="Model: [HAMMALE/mms-darija-finetuned](https://huggingface.co/HAMMALE/mms-darija-finetuned)",
+    examples=[
+        # You can add example audio files here if you have them
+    ],
+    cache_examples=False,
+    theme=gr.themes.Soft()
+)
+
+if __name__ == "__main__":
+    demo.launch()

checkpoint-1000/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2840e5e0a3373a4483fb4fa588ea832e45d43305b55ccac5233530fdd1db34e4
+size 3859521176

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e3aae72f2fe0371afdfb4fbc827842f2643e4b50c0e839c1dc9d9a4ef9d3e9
+size 7686012659

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dda9e7edbad7e1f2ea9b88ea55f72ba9c14c99c293a599e98092f98f8fb1ae0
+size 14709

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37bb1581d202aa22ea74daa929181abdfb2a3fa33a6d916b965e475f8b8905b1
+size 1383

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be48007f207c421506e912144b194f5d92eee8abae75376301624430209a58a
+size 1465

checkpoint-1000/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.250485358356253,
+  "best_model_checkpoint": "mms-darija-finetuned/checkpoint-1000",
+  "epoch": 1.1286681715575622,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11286681715575621,
+      "grad_norm": 2.7396411895751953,
+      "learning_rate": 5.88e-05,
+      "loss": 2.3959,
+      "step": 100
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 2.7468762397766113,
+      "learning_rate": 0.0001188,
+      "loss": 0.5308,
+      "step": 200
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "grad_norm": 2.6180174350738525,
+      "learning_rate": 0.00017879999999999998,
+      "loss": 0.53,
+      "step": 300
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 2.046238660812378,
+      "learning_rate": 0.0002388,
+      "loss": 0.5489,
+      "step": 400
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "grad_norm": 2.4370131492614746,
+      "learning_rate": 0.0002982,
+      "loss": 0.5507,
+      "step": 500
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "eval_loss": 0.32221749424934387,
+      "eval_runtime": 49.3694,
+      "eval_samples_per_second": 31.923,
+      "eval_steps_per_second": 15.961,
+      "eval_wer": 0.38112764924769454,
+      "step": 500
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 0.8341818451881409,
+      "learning_rate": 0.0002965191387559808,
+      "loss": 0.5311,
+      "step": 600
+    },
+    {
+      "epoch": 0.7900677200902935,
+      "grad_norm": 0.6782581210136414,
+      "learning_rate": 0.00029293062200956934,
+      "loss": 0.4588,
+      "step": 700
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.4923579692840576,
+      "learning_rate": 0.00028934210526315783,
+      "loss": 0.3537,
+      "step": 800
+    },
+    {
+      "epoch": 1.0158013544018059,
+      "grad_norm": 0.758439302444458,
+      "learning_rate": 0.0002857535885167464,
+      "loss": 0.375,
+      "step": 900
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "grad_norm": 0.712623119354248,
+      "learning_rate": 0.0002821650717703349,
+      "loss": 0.3764,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "eval_loss": 0.28351786732673645,
+      "eval_runtime": 48.5264,
+      "eval_samples_per_second": 32.477,
+      "eval_steps_per_second": 16.239,
+      "eval_wer": 0.250485358356253,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5035300125095938e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e049bd7921eb48f996e726c39ae31633a72809a2ae3db8056230d9b767c6a3
+size 5713

checkpoint-1500/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575f59479f8b3633fddcb5a7beab9bce91620ffe36bd68e87d4c96cd78392d47
+size 3859521176

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10c9c5099f71b6f921a96eba107c9a3a9fb36274dfae6cda0f1cb5321037163
+size 7686012659

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e9becf39296478be8cdd62efb4615adb5468be1464023d29e1ad944a51605b
+size 14709

checkpoint-1500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59575f2c6feaf27bb4a927c2c0d53a080cc10e83e7738fc167f66129f6dc7670
+size 1383

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32669f0fa422025ae7cdba910e1f0a84f65bbb7f79fa856c8bba9eebd541bc0a
+size 1465

checkpoint-1500/trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_global_step": 1500,
+  "best_metric": 0.21003882866850024,
+  "best_model_checkpoint": "mms-darija-finetuned/checkpoint-1500",
+  "epoch": 1.6930022573363432,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11286681715575621,
+      "grad_norm": 2.7396411895751953,
+      "learning_rate": 5.88e-05,
+      "loss": 2.3959,
+      "step": 100
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 2.7468762397766113,
+      "learning_rate": 0.0001188,
+      "loss": 0.5308,
+      "step": 200
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "grad_norm": 2.6180174350738525,
+      "learning_rate": 0.00017879999999999998,
+      "loss": 0.53,
+      "step": 300
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 2.046238660812378,
+      "learning_rate": 0.0002388,
+      "loss": 0.5489,
+      "step": 400
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "grad_norm": 2.4370131492614746,
+      "learning_rate": 0.0002982,
+      "loss": 0.5507,
+      "step": 500
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "eval_loss": 0.32221749424934387,
+      "eval_runtime": 49.3694,
+      "eval_samples_per_second": 31.923,
+      "eval_steps_per_second": 15.961,
+      "eval_wer": 0.38112764924769454,
+      "step": 500
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 0.8341818451881409,
+      "learning_rate": 0.0002965191387559808,
+      "loss": 0.5311,
+      "step": 600
+    },
+    {
+      "epoch": 0.7900677200902935,
+      "grad_norm": 0.6782581210136414,
+      "learning_rate": 0.00029293062200956934,
+      "loss": 0.4588,
+      "step": 700
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.4923579692840576,
+      "learning_rate": 0.00028934210526315783,
+      "loss": 0.3537,
+      "step": 800
+    },
+    {
+      "epoch": 1.0158013544018059,
+      "grad_norm": 0.758439302444458,
+      "learning_rate": 0.0002857535885167464,
+      "loss": 0.375,
+      "step": 900
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "grad_norm": 0.712623119354248,
+      "learning_rate": 0.0002821650717703349,
+      "loss": 0.3764,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "eval_loss": 0.28351786732673645,
+      "eval_runtime": 48.5264,
+      "eval_samples_per_second": 32.477,
+      "eval_steps_per_second": 16.239,
+      "eval_wer": 0.250485358356253,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2415349887133182,
+      "grad_norm": 0.4382162094116211,
+      "learning_rate": 0.0002785765550239234,
+      "loss": 0.3205,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "grad_norm": 5.204100131988525,
+      "learning_rate": 0.00027498803827751196,
+      "loss": 0.3739,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4672686230248306,
+      "grad_norm": 0.893830418586731,
+      "learning_rate": 0.00027139952153110045,
+      "loss": 0.2979,
+      "step": 1300
+    },
+    {
+      "epoch": 1.580135440180587,
+      "grad_norm": 0.426662415266037,
+      "learning_rate": 0.000267811004784689,
+      "loss": 0.3017,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "grad_norm": 0.4134344458580017,
+      "learning_rate": 0.0002642224880382775,
+      "loss": 0.2575,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "eval_loss": 0.19595518708229065,
+      "eval_runtime": 58.1681,
+      "eval_samples_per_second": 27.094,
+      "eval_steps_per_second": 13.547,
+      "eval_wer": 0.21003882866850024,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.256611183513416e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e049bd7921eb48f996e726c39ae31633a72809a2ae3db8056230d9b767c6a3
+size 5713

checkpoint-2000/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a221fc95c57e6200dd7e661b0c997ca8954a15016cd7f5bc0cf319d9f7244528
+size 3859521176

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed49f9a59d57ff6914314eb71f624ed68f547b36c55b81910b91762db375655b
+size 7686012659

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0bbe6d08d335cc8bb9ebc70e4c641eb2edde72bae1e631fd648b17db81fc267
+size 14709

checkpoint-2000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6af8c84c84b3d38abbacb49b636d4c0d288e97bb1e4c1dab714289dd100208
+size 1383

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194cdd674af00063e2d937369d227b46a8b8f2fe4d95aff0e801d7a579175691
+size 1465

checkpoint-2000/trainer_state.json

@@ -0,0 +1,219 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 0.18823814916680148,
+  "best_model_checkpoint": "mms-darija-finetuned/checkpoint-2000",
+  "epoch": 2.2573363431151243,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11286681715575621,
+      "grad_norm": 2.7396411895751953,
+      "learning_rate": 5.88e-05,
+      "loss": 2.3959,
+      "step": 100
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 2.7468762397766113,
+      "learning_rate": 0.0001188,
+      "loss": 0.5308,
+      "step": 200
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "grad_norm": 2.6180174350738525,
+      "learning_rate": 0.00017879999999999998,
+      "loss": 0.53,
+      "step": 300
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 2.046238660812378,
+      "learning_rate": 0.0002388,
+      "loss": 0.5489,
+      "step": 400
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "grad_norm": 2.4370131492614746,
+      "learning_rate": 0.0002982,
+      "loss": 0.5507,
+      "step": 500
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "eval_loss": 0.32221749424934387,
+      "eval_runtime": 49.3694,
+      "eval_samples_per_second": 31.923,
+      "eval_steps_per_second": 15.961,
+      "eval_wer": 0.38112764924769454,
+      "step": 500
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 0.8341818451881409,
+      "learning_rate": 0.0002965191387559808,
+      "loss": 0.5311,
+      "step": 600
+    },
+    {
+      "epoch": 0.7900677200902935,
+      "grad_norm": 0.6782581210136414,
+      "learning_rate": 0.00029293062200956934,
+      "loss": 0.4588,
+      "step": 700
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.4923579692840576,
+      "learning_rate": 0.00028934210526315783,
+      "loss": 0.3537,
+      "step": 800
+    },
+    {
+      "epoch": 1.0158013544018059,
+      "grad_norm": 0.758439302444458,
+      "learning_rate": 0.0002857535885167464,
+      "loss": 0.375,
+      "step": 900
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "grad_norm": 0.712623119354248,
+      "learning_rate": 0.0002821650717703349,
+      "loss": 0.3764,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "eval_loss": 0.28351786732673645,
+      "eval_runtime": 48.5264,
+      "eval_samples_per_second": 32.477,
+      "eval_steps_per_second": 16.239,
+      "eval_wer": 0.250485358356253,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2415349887133182,
+      "grad_norm": 0.4382162094116211,
+      "learning_rate": 0.0002785765550239234,
+      "loss": 0.3205,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "grad_norm": 5.204100131988525,
+      "learning_rate": 0.00027498803827751196,
+      "loss": 0.3739,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4672686230248306,
+      "grad_norm": 0.893830418586731,
+      "learning_rate": 0.00027139952153110045,
+      "loss": 0.2979,
+      "step": 1300
+    },
+    {
+      "epoch": 1.580135440180587,
+      "grad_norm": 0.426662415266037,
+      "learning_rate": 0.000267811004784689,
+      "loss": 0.3017,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "grad_norm": 0.4134344458580017,
+      "learning_rate": 0.0002642224880382775,
+      "loss": 0.2575,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "eval_loss": 0.19595518708229065,
+      "eval_runtime": 58.1681,
+      "eval_samples_per_second": 27.094,
+      "eval_steps_per_second": 13.547,
+      "eval_wer": 0.21003882866850024,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "grad_norm": 1.7899537086486816,
+      "learning_rate": 0.000260633971291866,
+      "loss": 0.2805,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9187358916478554,
+      "grad_norm": 0.36495277285575867,
+      "learning_rate": 0.0002570454545454545,
+      "loss": 0.2567,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0316027088036117,
+      "grad_norm": 0.4699445068836212,
+      "learning_rate": 0.00025345693779904306,
+      "loss": 0.2234,
+      "step": 1800
+    },
+    {
+      "epoch": 2.144469525959368,
+      "grad_norm": 0.6241821646690369,
+      "learning_rate": 0.00024986842105263155,
+      "loss": 0.2331,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "grad_norm": 0.5561006665229797,
+      "learning_rate": 0.00024631578947368417,
+      "loss": 0.2519,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "eval_loss": 0.1508670300245285,
+      "eval_runtime": 47.958,
+      "eval_samples_per_second": 32.862,
+      "eval_steps_per_second": 16.431,
+      "eval_wer": 0.18823814916680148,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.004473369008046e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e049bd7921eb48f996e726c39ae31633a72809a2ae3db8056230d9b767c6a3
+size 5713

checkpoint-2500/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a132b2753ce6ded08dfc70b9dd315d50a15033eb0640dd5e275d06ac794006
+size 3859521176

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca018b139d013b53efd41b63aa5c7c87120fbaee22d2e926a9a7e1555a18a75
+size 7686012659

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8d79f63b2f87f840f2d64ead18ac3510040553c28f44f5c4f2265b02365327
+size 14709

checkpoint-2500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d4f81509232003d5e6c179ff0078f6becbd8bc508439a20f21939ccba8ae7d
+size 1383

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9a463e4b195573c6e3a3087023d396ca4d0bc7418bfd033429d7cc80f73a89
+size 1465

checkpoint-2500/trainer_state.json

@@ -0,0 +1,263 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 0.18823814916680148,
+  "best_model_checkpoint": "mms-darija-finetuned/checkpoint-2000",
+  "epoch": 2.8216704288939054,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11286681715575621,
+      "grad_norm": 2.7396411895751953,
+      "learning_rate": 5.88e-05,
+      "loss": 2.3959,
+      "step": 100
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 2.7468762397766113,
+      "learning_rate": 0.0001188,
+      "loss": 0.5308,
+      "step": 200
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "grad_norm": 2.6180174350738525,
+      "learning_rate": 0.00017879999999999998,
+      "loss": 0.53,
+      "step": 300
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 2.046238660812378,
+      "learning_rate": 0.0002388,
+      "loss": 0.5489,
+      "step": 400
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "grad_norm": 2.4370131492614746,
+      "learning_rate": 0.0002982,
+      "loss": 0.5507,
+      "step": 500
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "eval_loss": 0.32221749424934387,
+      "eval_runtime": 49.3694,
+      "eval_samples_per_second": 31.923,
+      "eval_steps_per_second": 15.961,
+      "eval_wer": 0.38112764924769454,
+      "step": 500
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 0.8341818451881409,
+      "learning_rate": 0.0002965191387559808,
+      "loss": 0.5311,
+      "step": 600
+    },
+    {
+      "epoch": 0.7900677200902935,
+      "grad_norm": 0.6782581210136414,
+      "learning_rate": 0.00029293062200956934,
+      "loss": 0.4588,
+      "step": 700
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.4923579692840576,
+      "learning_rate": 0.00028934210526315783,
+      "loss": 0.3537,
+      "step": 800
+    },
+    {
+      "epoch": 1.0158013544018059,
+      "grad_norm": 0.758439302444458,
+      "learning_rate": 0.0002857535885167464,
+      "loss": 0.375,
+      "step": 900
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "grad_norm": 0.712623119354248,
+      "learning_rate": 0.0002821650717703349,
+      "loss": 0.3764,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "eval_loss": 0.28351786732673645,
+      "eval_runtime": 48.5264,
+      "eval_samples_per_second": 32.477,
+      "eval_steps_per_second": 16.239,
+      "eval_wer": 0.250485358356253,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2415349887133182,
+      "grad_norm": 0.4382162094116211,
+      "learning_rate": 0.0002785765550239234,
+      "loss": 0.3205,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "grad_norm": 5.204100131988525,
+      "learning_rate": 0.00027498803827751196,
+      "loss": 0.3739,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4672686230248306,
+      "grad_norm": 0.893830418586731,
+      "learning_rate": 0.00027139952153110045,
+      "loss": 0.2979,
+      "step": 1300
+    },
+    {
+      "epoch": 1.580135440180587,
+      "grad_norm": 0.426662415266037,
+      "learning_rate": 0.000267811004784689,
+      "loss": 0.3017,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "grad_norm": 0.4134344458580017,
+      "learning_rate": 0.0002642224880382775,
+      "loss": 0.2575,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "eval_loss": 0.19595518708229065,
+      "eval_runtime": 58.1681,
+      "eval_samples_per_second": 27.094,
+      "eval_steps_per_second": 13.547,
+      "eval_wer": 0.21003882866850024,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "grad_norm": 1.7899537086486816,
+      "learning_rate": 0.000260633971291866,
+      "loss": 0.2805,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9187358916478554,
+      "grad_norm": 0.36495277285575867,
+      "learning_rate": 0.0002570454545454545,
+      "loss": 0.2567,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0316027088036117,
+      "grad_norm": 0.4699445068836212,
+      "learning_rate": 0.00025345693779904306,
+      "loss": 0.2234,
+      "step": 1800
+    },
+    {
+      "epoch": 2.144469525959368,
+      "grad_norm": 0.6241821646690369,
+      "learning_rate": 0.00024986842105263155,
+      "loss": 0.2331,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "grad_norm": 0.5561006665229797,
+      "learning_rate": 0.00024631578947368417,
+      "loss": 0.2519,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "eval_loss": 0.1508670300245285,
+      "eval_runtime": 47.958,
+      "eval_samples_per_second": 32.862,
+      "eval_steps_per_second": 16.431,
+      "eval_wer": 0.18823814916680148,
+      "step": 2000
+    },
+    {
+      "epoch": 2.37020316027088,
+      "grad_norm": 0.5059154033660889,
+      "learning_rate": 0.0002427272727272727,
+      "loss": 0.2144,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4830699774266365,
+      "grad_norm": 0.5262096524238586,
+      "learning_rate": 0.00023913875598086123,
+      "loss": 0.2034,
+      "step": 2200
+    },
+    {
+      "epoch": 2.595936794582393,
+      "grad_norm": 0.46527203917503357,
+      "learning_rate": 0.00023555023923444972,
+      "loss": 0.201,
+      "step": 2300
+    },
+    {
+      "epoch": 2.708803611738149,
+      "grad_norm": 3.4555609226226807,
+      "learning_rate": 0.00023196172248803824,
+      "loss": 0.2248,
+      "step": 2400
+    },
+    {
+      "epoch": 2.8216704288939054,
+      "grad_norm": 0.497281938791275,
+      "learning_rate": 0.00022837320574162676,
+      "loss": 0.2515,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8216704288939054,
+      "eval_loss": 0.17336268723011017,
+      "eval_runtime": 49.1468,
+      "eval_samples_per_second": 32.067,
+      "eval_steps_per_second": 16.034,
+      "eval_wer": 0.1939815563824624,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.7579227205569675e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e049bd7921eb48f996e726c39ae31633a72809a2ae3db8056230d9b767c6a3
+size 5713

checkpoint-3000/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512
+}

checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8242023b491381e4f595c2e69aacb3c51066600428ef42b58accfc8c65e8d432
+size 3859521176

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97855f6703b7ceabac1a46c6ba3c259417727e8f7aa93beb6d7aba2845704153
+size 7686012659

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee68bd8550ab0601f2aabc6a49ba6790e07dc6599d8fbc38cc02e0aeed39d34c
+size 14709

checkpoint-3000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a0dc82f610208770bebb932d695a43fcf87277d31d9d5bca339ba51c41ce3a
+size 1383

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b520150ed007dadc448186006366134cd4e755edaed99c2cfe231eacf21cd4f
+size 1465

checkpoint-3000/trainer_state.json

@@ -0,0 +1,307 @@
+{
+  "best_global_step": 3000,
+  "best_metric": 0.16409157094321308,
+  "best_model_checkpoint": "mms-darija-finetuned/checkpoint-3000",
+  "epoch": 3.386004514672686,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11286681715575621,
+      "grad_norm": 2.7396411895751953,
+      "learning_rate": 5.88e-05,
+      "loss": 2.3959,
+      "step": 100
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 2.7468762397766113,
+      "learning_rate": 0.0001188,
+      "loss": 0.5308,
+      "step": 200
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "grad_norm": 2.6180174350738525,
+      "learning_rate": 0.00017879999999999998,
+      "loss": 0.53,
+      "step": 300
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 2.046238660812378,
+      "learning_rate": 0.0002388,
+      "loss": 0.5489,
+      "step": 400
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "grad_norm": 2.4370131492614746,
+      "learning_rate": 0.0002982,
+      "loss": 0.5507,
+      "step": 500
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "eval_loss": 0.32221749424934387,
+      "eval_runtime": 49.3694,
+      "eval_samples_per_second": 31.923,
+      "eval_steps_per_second": 15.961,
+      "eval_wer": 0.38112764924769454,
+      "step": 500
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 0.8341818451881409,
+      "learning_rate": 0.0002965191387559808,
+      "loss": 0.5311,
+      "step": 600
+    },
+    {
+      "epoch": 0.7900677200902935,
+      "grad_norm": 0.6782581210136414,
+      "learning_rate": 0.00029293062200956934,
+      "loss": 0.4588,
+      "step": 700
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.4923579692840576,
+      "learning_rate": 0.00028934210526315783,
+      "loss": 0.3537,
+      "step": 800
+    },
+    {
+      "epoch": 1.0158013544018059,
+      "grad_norm": 0.758439302444458,
+      "learning_rate": 0.0002857535885167464,
+      "loss": 0.375,
+      "step": 900
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "grad_norm": 0.712623119354248,
+      "learning_rate": 0.0002821650717703349,
+      "loss": 0.3764,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1286681715575622,
+      "eval_loss": 0.28351786732673645,
+      "eval_runtime": 48.5264,
+      "eval_samples_per_second": 32.477,
+      "eval_steps_per_second": 16.239,
+      "eval_wer": 0.250485358356253,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2415349887133182,
+      "grad_norm": 0.4382162094116211,
+      "learning_rate": 0.0002785765550239234,
+      "loss": 0.3205,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3544018058690745,
+      "grad_norm": 5.204100131988525,
+      "learning_rate": 0.00027498803827751196,
+      "loss": 0.3739,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4672686230248306,
+      "grad_norm": 0.893830418586731,
+      "learning_rate": 0.00027139952153110045,
+      "loss": 0.2979,
+      "step": 1300
+    },
+    {
+      "epoch": 1.580135440180587,
+      "grad_norm": 0.426662415266037,
+      "learning_rate": 0.000267811004784689,
+      "loss": 0.3017,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "grad_norm": 0.4134344458580017,
+      "learning_rate": 0.0002642224880382775,
+      "loss": 0.2575,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6930022573363432,
+      "eval_loss": 0.19595518708229065,
+      "eval_runtime": 58.1681,
+      "eval_samples_per_second": 27.094,
+      "eval_steps_per_second": 13.547,
+      "eval_wer": 0.21003882866850024,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8058690744920993,
+      "grad_norm": 1.7899537086486816,
+      "learning_rate": 0.000260633971291866,
+      "loss": 0.2805,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9187358916478554,
+      "grad_norm": 0.36495277285575867,
+      "learning_rate": 0.0002570454545454545,
+      "loss": 0.2567,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0316027088036117,
+      "grad_norm": 0.4699445068836212,
+      "learning_rate": 0.00025345693779904306,
+      "loss": 0.2234,
+      "step": 1800
+    },
+    {
+      "epoch": 2.144469525959368,
+      "grad_norm": 0.6241821646690369,
+      "learning_rate": 0.00024986842105263155,
+      "loss": 0.2331,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "grad_norm": 0.5561006665229797,
+      "learning_rate": 0.00024631578947368417,
+      "loss": 0.2519,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2573363431151243,
+      "eval_loss": 0.1508670300245285,
+      "eval_runtime": 47.958,
+      "eval_samples_per_second": 32.862,
+      "eval_steps_per_second": 16.431,
+      "eval_wer": 0.18823814916680148,
+      "step": 2000
+    },
+    {
+      "epoch": 2.37020316027088,
+      "grad_norm": 0.5059154033660889,
+      "learning_rate": 0.0002427272727272727,
+      "loss": 0.2144,
+      "step": 2100
+    },
+    {
+      "epoch": 2.4830699774266365,
+      "grad_norm": 0.5262096524238586,
+      "learning_rate": 0.00023913875598086123,
+      "loss": 0.2034,
+      "step": 2200
+    },
+    {
+      "epoch": 2.595936794582393,
+      "grad_norm": 0.46527203917503357,
+      "learning_rate": 0.00023555023923444972,
+      "loss": 0.201,
+      "step": 2300
+    },
+    {
+      "epoch": 2.708803611738149,
+      "grad_norm": 3.4555609226226807,
+      "learning_rate": 0.00023196172248803824,
+      "loss": 0.2248,
+      "step": 2400
+    },
+    {
+      "epoch": 2.8216704288939054,
+      "grad_norm": 0.497281938791275,
+      "learning_rate": 0.00022837320574162676,
+      "loss": 0.2515,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8216704288939054,
+      "eval_loss": 0.17336268723011017,
+      "eval_runtime": 49.1468,
+      "eval_samples_per_second": 32.067,
+      "eval_steps_per_second": 16.034,
+      "eval_wer": 0.1939815563824624,
+      "step": 2500
+    },
+    {
+      "epoch": 2.9345372460496613,
+      "grad_norm": 0.29302966594696045,
+      "learning_rate": 0.00022478468899521527,
+      "loss": 0.209,
+      "step": 2600
+    },
+    {
+      "epoch": 3.0474040632054176,
+      "grad_norm": 0.2737024426460266,
+      "learning_rate": 0.0002211961722488038,
+      "loss": 0.1449,
+      "step": 2700
+    },
+    {
+      "epoch": 3.160270880361174,
+      "grad_norm": 0.34064537286758423,
+      "learning_rate": 0.00021760765550239233,
+      "loss": 0.1597,
+      "step": 2800
+    },
+    {
+      "epoch": 3.27313769751693,
+      "grad_norm": 0.3498232662677765,
+      "learning_rate": 0.00021401913875598085,
+      "loss": 0.1855,
+      "step": 2900
+    },
+    {
+      "epoch": 3.386004514672686,
+      "grad_norm": 0.5131095051765442,
+      "learning_rate": 0.00021043062200956937,
+      "loss": 0.1715,
+      "step": 3000
+    },
+    {
+      "epoch": 3.386004514672686,
+      "eval_loss": 0.2065732479095459,
+      "eval_runtime": 48.3591,
+      "eval_samples_per_second": 32.59,
+      "eval_steps_per_second": 16.295,
+      "eval_wer": 0.16409157094321308,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.506282119291601e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e049bd7921eb48f996e726c39ae31633a72809a2ae3db8056230d9b767c6a3
+size 5713

checkpoint-3500/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512
+}

checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99aeca7a440077a24f1c0b09897ed36f5a932570dd2496729faae5b4396914d3
+size 3859521176

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dfbc69b38fe026009bcc11b146b0c29cfb62bfd590ce87773a3d5d40ef0f29e
+size 7686012659

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5849d0d95cfbe5dd2e51751b724005066bf8a4a36b5dfb9defee57e73469572d
+size 14709

checkpoint-3500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f5e71a7a99649a841958dea51b3ddabaa13446a4bd011a06e48dc4379e99d1
+size 1383