Rename WhisperBot to WhisperFusion

README.md

@@ -1,8 +1,8 @@
-# WhisperBot
+# WhisperFusion
 
 
-Welcome to WhisperBot. WhisperBot builds upon the capabilities of the
-[WhisperLive](https://github.com/collabora/WhisperLive) and
+Welcome to WhisperFusion. WhisperFusion builds upon the capabilities of
+the [WhisperLive](https://github.com/collabora/WhisperLive) and
 [WhisperSpeech](https://github.com/collabora/WhisperSpeech) by
 integrating Mistral, a Large Language Model (LLM), on top of the
 real-time speech-to-text pipeline. WhisperLive relies on OpenAI Whisper,
@@ -149,17 +149,17 @@ cp -r phi-2 "$dest"
 cp -r "$phi_path" "$dest/phi-orig-model"
 ```
 
-## Build WhisperBot
+## Build WhisperFusion
 
 > [!NOTE]
 >
-> These steps are included in `docker/scripts/setup-whisperbot.sh`
+> These steps are included in `docker/scripts/setup-whisperfusion.sh`
 
 Clone this repo and install requirements
 
 ``` bash
-[ -d "WhisperBot" ] || git clone https://github.com/collabora/WhisperBot.git
-cd WhisperBot
+[ -d "WhisperFusion" ] || git clone https://github.com/collabora/WhisperFusion.git
+cd WhisperFusion
 apt update
 apt install ffmpeg portaudio19-dev -y
 ```
@@ -174,7 +174,6 @@ Install all the other dependencies normally
 
 ``` bash
 pip install -r requirements.txt
-pip install openai-whisper whisperspeech soundfile
 ```
 
 force update huggingface_hub (tokenizers 0.14.1 spuriously require and
@@ -191,7 +190,7 @@ curl -L -o /root/.cache/whisper-live/silero_vad.onnx https://github.com/snakers4
 python -c 'from transformers.utils.hub import move_cache; move_cache()'
 ```
 
-### Run WhisperBot with Whisper and Mistral/Phi-2
+### Run WhisperFusion with Whisper and Mistral/Phi-2
 
 Take the folder path for Whisper TensorRT model, folder_path and
 tokenizer_path for Mistral/Phi-2 TensorRT from the build phase. If a
@@ -200,11 +199,11 @@ huggingface repo name as the tokenizer path.
 
 > [!NOTE]
 >
-> These steps are included in `docker/scripts/run-whisperbot.sh`
+> These steps are included in `docker/scripts/run-whisperfusion.sh`
 
 ``` bash
 test -f /etc/shinit_v2 && source /etc/shinit_v2
-cd WhisperBot
+cd WhisperFusion
 if [ "$1" != "mistral" ]; then
   exec python3 main.py --phi \
                   --whisper_tensorrt_path /root/whisper_small_en \
@@ -222,7 +221,7 @@ fi
   execute `run_client.py`
 
 ``` bash
-cd WhisperBot
+cd WhisperFusion
 pip install -r requirements.txt
 python3 run_client.py
 ```

README.qmd

@@ -27,9 +27,9 @@ These steps are included in `{fname}`
     if code: print("```")
 ```
 
-# WhisperBot
+# WhisperFusion
 
-Welcome to WhisperBot. WhisperBot builds upon the capabilities of the [WhisperLive](https://github.com/collabora/WhisperLive) and [WhisperSpeech](https://github.com/collabora/WhisperSpeech) by integrating Mistral, a Large Language Model (LLM), on top of the real-time speech-to-text pipeline. WhisperLive relies on OpenAI Whisper, a powerful automatic speech recognition (ASR) system. Both Mistral and Whisper are optimized to run efficiently as TensorRT engines, maximizing performance and real-time processing capabilities.
+Welcome to WhisperFusion. WhisperFusion builds upon the capabilities of the [WhisperLive](https://github.com/collabora/WhisperLive) and [WhisperSpeech](https://github.com/collabora/WhisperSpeech) by integrating Mistral, a Large Language Model (LLM), on top of the real-time speech-to-text pipeline. WhisperLive relies on OpenAI Whisper, a powerful automatic speech recognition (ASR) system. Both Mistral and Whisper are optimized to run efficiently as TensorRT engines, maximizing performance and real-time processing capabilities.
 
 ## Features
 - **Real-Time Speech-to-Text**: Utilizes OpenAI WhisperLive to convert spoken language into text in real-time.
@@ -60,23 +60,23 @@ include_file('docker/scripts/build-mistral.sh')
 include_file('docker/scripts/build-phi-2.sh')
 ```
 
-## Build WhisperBot
+## Build WhisperFusion
 
 ```{python}
-include_file('docker/scripts/setup-whisperbot.sh')
+include_file('docker/scripts/setup-whisperfusion.sh')
 ```
 
-### Run WhisperBot with Whisper and Mistral/Phi-2
+### Run WhisperFusion with Whisper and Mistral/Phi-2
 
 Take the folder path for Whisper TensorRT model, folder_path and tokenizer_path for Mistral/Phi-2 TensorRT from the build phase. If a huggingface model is used to build mistral/phi-2 then just use the huggingface repo name as the tokenizer path.
 
 ```{python}
-include_file('docker/scripts/run-whisperbot.sh')
+include_file('docker/scripts/run-whisperfusion.sh')
 ```
 
 - On the client side clone the repo, install the requirements and execute `run_client.py`
 ```bash
-cd WhisperBot
+cd WhisperFusion
 pip install -r requirements.txt
 python3 run_client.py
 ```

docker/Dockerfile

@@ -1,8 +1,8 @@
-FROM ghcr.io/collabora/whisperbot-base:latest as base
+FROM ghcr.io/collabora/whisperfusion-base:latest as base
 
 WORKDIR /root
-COPY scripts/setup-whisperbot.sh scripts/run-whisperbot.sh scratch-space/models /root/
-RUN ./setup-whisperbot.sh
+COPY scripts/setup-whisperfusion.sh scripts/run-whisperfusion.sh scratch-space/models /root/
+RUN ./setup-whisperfusion.sh
 
-CMD ./run-whisperbot.sh
+CMD ./run-whisperfusion.sh
 

docker/build.sh

@@ -4,11 +4,11 @@
 
 (
   cd base-image &&
-  docker build $ARGS -t ghcr.io/collabora/whisperbot-base:latest .
+  docker build $ARGS -t ghcr.io/collabora/whisperfusion-base:latest .
 )
 
 mkdir -p scratch-space
 cp -r scripts/build-* scratch-space
-#docker run --gpus all --shm-size 64G -v "$PWD"/scratch-space:/root/scratch-space -w /root/scratch-space -it ghcr.io/collabora/whisperbot-base:latest ./build-models.sh
+docker run --gpus all --shm-size 64G -v "$PWD"/scratch-space:/root/scratch-space -w /root/scratch-space -it ghcr.io/collabora/whisperfusion-base:latest ./build-models.sh
 
-docker build $ARGS -t ghcr.io/collabora/whisperbot:latest .
+docker build $ARGS -t ghcr.io/collabora/whisperfusion:latest .

docker/publish.sh

@@ -1,4 +1,4 @@
 #!/bin/bash -e
 
-docker push ghcr.io/collabora/whisperbot-base:latest
-docker push ghcr.io/collabora/whisperbot:latest
+docker push ghcr.io/collabora/whisperfusion-base:latest
+docker push ghcr.io/collabora/whisperfusion:latest

docker/scripts/{run-whisperbot.sh → run-whisperfusion.sh}

@@ -2,7 +2,7 @@
 
 test -f /etc/shinit_v2 && source /etc/shinit_v2
 
-cd WhisperBot
+cd WhisperFusion
 if [ "$1" != "mistral" ]; then
   exec python3 main.py --phi \
                   --whisper_tensorrt_path /root/whisper_small_en \

docker/scripts/{setup-whisperbot.sh → setup-whisperfusion.sh}

@@ -1,9 +1,9 @@
 #!/bin/bash -e
 
 ## Clone this repo and install requirements
-[ -d "WhisperBot" ] || git clone https://github.com/collabora/WhisperBot.git
+[ -d "WhisperFusion" ] || git clone https://github.com/collabora/WhisperFusion.git
 
-cd WhisperBot
+cd WhisperFusion
 apt update
 apt install ffmpeg portaudio19-dev -y
 

docker/scripts/setup.sh

@@ -3,4 +3,4 @@
 ./setup-whisper.sh
 #./setup-mistral.sh
 ./setup-phi-2.sh
-./setup-whisperbot.sh
+./setup-whisperfusion.sh