Refactor Dockerfile and requirements for improved dependency management and clarity

Dockerfile

@@ -9,8 +9,8 @@ RUN apt-get update && apt-get install -y \
     curl \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements first for better caching
-COPY requirements-hf.txt ./requirements.txt
+# Copy requirements file first for better caching
+COPY requirements.txt ./requirements.txt
 
 # Install Python dependencies
 RUN pip install --no-cache-dir -r requirements.txt

TRAINING_GUIDE.md

@@ -111,27 +111,31 @@ def synthesize_speech(text, speaker_id=0):
 
 ## 🎯 Training Configurations
 
-### For Different Environments:
+### For Different Environments
 
 1. **Local Development** (Single GPU):
+
    ```bash
    export CUDA_VISIBLE_DEVICES="0"
    python speech/train.py --config speech/config.yaml --model llm ...
    ```
 
 2. **Multi-GPU Training**:
+
    ```bash
    export CUDA_VISIBLE_DEVICES="0,1,2,3"
    torchrun --nproc_per_node=4 speech/train.py ...
    ```
 
 3. **Cloud Training** (Google Colab/Kaggle):
+
    ```python
    # Use config_hf.yaml for resource-constrained environments
    !python speech/train.py --config speech/config_hf.yaml ...
    ```
 
 4. **Hugging Face Spaces**:
+
    ```bash
    # For direct training on HF infrastructure
    python speech/train.py --config speech/config_hf.yaml --timeout 1800 ...
@@ -140,6 +144,7 @@ def synthesize_speech(text, speaker_id=0):
 ## 📊 Monitoring Training
 
 1. **Comet ML** (Recommended):
+
    ```bash
    # Set up Comet ML for experiment tracking
    export COMET_API_KEY="your_api_key"
@@ -147,11 +152,13 @@ def synthesize_speech(text, speaker_id=0):
    ```
 
 2. **Tensorboard**:
+
    ```bash
    tensorboard --logdir ./tensorboard
    ```
 
 3. **Command Line**:
+
    ```bash
    # Monitor log files
    tail -f checkpoints/llm/train.log
@@ -159,7 +166,7 @@ def synthesize_speech(text, speaker_id=0):
 
 ## 🔧 Troubleshooting
 
-### Common Issues:
+### Common Issues
 
 1. **Out of Memory**:
    - Reduce batch size in config
@@ -176,9 +183,10 @@ def synthesize_speech(text, speaker_id=0):
    - Verify data preprocessing
    - Use pretrained checkpoints
 
-### Performance Tips:
+### Performance Tips
 
 1. **Data Loading Optimization**:
+
    ```yaml
    # In config.yaml
    num_workers: 24
@@ -187,12 +195,14 @@ def synthesize_speech(text, speaker_id=0):
    ```
 
 2. **Memory Optimization**:
+
    ```bash
    # Use gradient checkpointing
    --use_amp --accum_grad 2
    ```
 
 3. **Speed Optimization**:
+
    ```bash
    # Compile model for faster training (PyTorch 2.0+)
    export TORCH_COMPILE=1

requirements-hf.txt

@@ -1,14 +0,0 @@
-gradio==3.50.2
-torch==2.1.0
-torchaudio==2.1.0
-numpy==1.24.3
-soundfile==0.12.1
-librosa==0.10.1
-transformers==4.36.0
-omegaconf==2.3.0
-hydra-core==1.3.2
-
-# Optional: Add these if you need the full training pipeline
-# deepspeed==0.12.6
-# tensorboard==2.14.0
-# matplotlib==3.7.2

requirements.txt

@@ -17,6 +17,7 @@ lightning==2.2.4
 matplotlib==3.7.5
 modelscope==1.20.0
 networkx==3.1
+numpy==1.24.3
 omegaconf==2.3.0
 onnx==1.16.0
 onnxruntime-gpu==1.18.0; sys_platform == 'linux'
@@ -41,4 +42,9 @@ wget==3.2
 flatten_dict
 julius
 importlib_resources
-randomname
+randomname
+
+# Optional: Add these if you need the full training pipeline
+# deepspeed==0.12.6
+# tensorboard==2.14.0
+# matplotlib==3.7.2