chore: Minor improvements and fixes

README.md

@@ -12,6 +12,8 @@ app_file: src/pronunciation_trainer/app.py
 This repository/app showcases how a [phoneme-based pronunciation trainer](https://github.com/pwenker/pronunciation_trainer/blob/main/docs/phoneme_based_solution.md)
 (including personalized LLM-based feedback) overcomes the limitations of a [grapheme-based approach](https://github.com/pwenker/pronunciation_trainer/blob/main/docs/grapheme_based_solution.md)
 
+For convenience, you find a feature comparison overview of the two solutions below:
+
 | Feature                           | Grapheme-Based Solution                                  | Phoneme-Based Solution                                  |
 |-----------------------------------|----------------------------------------------------------|---------------------------------------------------------|
 | **Input Type**                    | Text transcriptions of speech                            | Audio files and phoneme transcriptions                  |
@@ -30,13 +32,13 @@ This repository/app showcases how a [phoneme-based pronunciation trainer](https:
 ## Quickstart 🚀
 
 ### 👉 Click here to try out the app directly:
-[**Pronunciation Trainer App**](https://pwenker-pronunciation_trainer.hf.space/)
+[**Pronunciation Trainer App**](https://pwenker-pronunciation-trainer.hf.space/)
 
 ### 🔍 Inspect the code at:
-- **GitHub:** [pwenker/pronunciation_trainer](https://github.com/pwenker/pronounciation_trainer)
-- **Hugging Face Spaces:** [pwenker/pronunciation_trainer](https://huggingface.co/spaces/pwenker/pronounciation_trainer)
+- **GitHub:** [pwenker/pronunciation_trainer](https://github.com/pwenker/pronunciation_trainer)
+- **Hugging Face Spaces:** [pwenker/pronunciation_trainer](https://huggingface.co/spaces/pwenker/pronunciation_trainer)
 
-### 📚 Read about the pronounciation trainer:
+### 📚 Read about the pronunciation trainer:
 
 1. [Grapheme-based Approach](https://github.com/pwenker/pronunciation_trainer/blob/main/docs/grapheme_based_solution.md)
 2. [Phoneme-based Approach](https://github.com/pwenker/pronunciation_trainer/blob/main/docs/phoneme_based_solution.md)

no_header_readme.md

@@ -3,6 +3,8 @@
 This repository/app showcases how a [phoneme-based pronunciation trainer](https://github.com/pwenker/pronunciation_trainer/blob/main/docs/phoneme_based_solution.md)
 (including personalized LLM-based feedback) overcomes the limitations of a [grapheme-based approach](https://github.com/pwenker/pronunciation_trainer/blob/main/docs/grapheme_based_solution.md)
 
+For convenience, you find a feature comparison overview of the two solutions below:
+
 | Feature                           | Grapheme-Based Solution                                  | Phoneme-Based Solution                                  |
 |-----------------------------------|----------------------------------------------------------|---------------------------------------------------------|
 | **Input Type**                    | Text transcriptions of speech                            | Audio files and phoneme transcriptions                  |
@@ -21,13 +23,13 @@ This repository/app showcases how a [phoneme-based pronunciation trainer](https:
 ## Quickstart 🚀
 
 ### 👉 Click here to try out the app directly:
-[**Pronunciation Trainer App**](https://pwenker-pronunciation_trainer.hf.space/)
+[**Pronunciation Trainer App**](https://pwenker-pronunciation-trainer.hf.space/)
 
 ### 🔍 Inspect the code at:
-- **GitHub:** [pwenker/pronunciation_trainer](https://github.com/pwenker/pronounciation_trainer)
-- **Hugging Face Spaces:** [pwenker/pronunciation_trainer](https://huggingface.co/spaces/pwenker/pronounciation_trainer)
+- **GitHub:** [pwenker/pronunciation_trainer](https://github.com/pwenker/pronunciation_trainer)
+- **Hugging Face Spaces:** [pwenker/pronunciation_trainer](https://huggingface.co/spaces/pwenker/pronunciation_trainer)
 
-### 📚 Read about the pronounciation trainer:
+### 📚 Read about the pronunciation trainer:
 
 1. [Grapheme-based Approach](https://github.com/pwenker/pronunciation_trainer/blob/main/docs/grapheme_based_solution.md)
 2. [Phoneme-based Approach](https://github.com/pwenker/pronunciation_trainer/blob/main/docs/phoneme_based_solution.md)

requirements-dev.lock

@@ -5,143 +5,406 @@
 #   pre: false
 #   features: []
 #   all-features: false
+#   with-sources: false
 
 -e file:.
 aiofiles==23.2.1
+    # via gradio
 aiohttp==3.9.5
+    # via langchain
+    # via langchain-community
 aiosignal==1.3.1
+    # via aiohttp
 altair==5.3.0
+    # via gradio
 annotated-types==0.6.0
+    # via pydantic
 anyio==4.3.0
+    # via httpx
+    # via openai
+    # via starlette
+    # via watchfiles
+async-timeout==4.0.3
+    # via aiohttp
+    # via langchain
 attrs==23.2.0
+    # via aiohttp
+    # via clldutils
+    # via csvw
+    # via jsonschema
+    # via phonemizer
+    # via referencing
 babel==2.15.0
+    # via csvw
 bibtexparser==2.0.0b7
+    # via clldutils
 certifi==2024.2.2
+    # via httpcore
+    # via httpx
+    # via requests
 charset-normalizer==3.3.2
+    # via requests
 click==8.1.7
+    # via typer
+    # via uvicorn
 clldutils==3.22.2
+    # via segments
 colorama==0.4.6
+    # via csvw
 colorlog==6.8.2
+    # via clldutils
 contourpy==1.2.1
+    # via matplotlib
 csvw==3.3.0
+    # via segments
 cycler==0.12.1
+    # via matplotlib
 dataclasses-json==0.6.5
+    # via langchain
+    # via langchain-community
 distro==1.9.0
+    # via openai
 dlinfo==1.2.1
+    # via phonemizer
 dnspython==2.6.1
+    # via email-validator
 email-validator==2.1.1
+    # via fastapi
+exceptiongroup==1.2.1
+    # via anyio
 fastapi==0.111.0
+    # via fastapi-cli
+    # via gradio
 fastapi-cli==0.0.3
+    # via fastapi
 ffmpy==0.3.2
+    # via gradio
 filelock==3.14.0
+    # via huggingface-hub
+    # via torch
+    # via transformers
+    # via triton
 fonttools==4.51.0
+    # via matplotlib
 frozenlist==1.4.1
+    # via aiohttp
+    # via aiosignal
 fsspec==2024.3.1
+    # via gradio-client
+    # via huggingface-hub
+    # via torch
 gradio==4.29.0
+    # via pronunciation-trainer
 gradio-client==0.16.1
+    # via gradio
 greenlet==3.0.3
+    # via sqlalchemy
 h11==0.14.0
+    # via httpcore
+    # via uvicorn
 httpcore==1.0.5
+    # via httpx
 httptools==0.6.1
+    # via uvicorn
 httpx==0.27.0
+    # via fastapi
+    # via gradio
+    # via gradio-client
+    # via openai
 huggingface-hub==0.23.0
+    # via gradio
+    # via gradio-client
+    # via tokenizers
+    # via transformers
 idna==3.7
+    # via anyio
+    # via email-validator
+    # via httpx
+    # via requests
+    # via yarl
 importlib-resources==6.4.0
+    # via gradio
 isodate==0.6.1
+    # via csvw
+    # via rdflib
 jinja2==3.1.4
+    # via altair
+    # via fastapi
+    # via gradio
+    # via torch
 joblib==1.4.2
+    # via phonemizer
 jsonpatch==1.33
+    # via langchain-core
 jsonpointer==2.4
+    # via jsonpatch
 jsonschema==4.22.0
+    # via altair
+    # via csvw
 jsonschema-specifications==2023.12.1
+    # via jsonschema
 kiwisolver==1.4.5
+    # via matplotlib
 langchain==0.1.19
+    # via pronunciation-trainer
 langchain-community==0.0.38
+    # via langchain
 langchain-core==0.1.52
+    # via langchain
+    # via langchain-community
+    # via langchain-openai
+    # via langchain-text-splitters
 langchain-openai==0.1.6
+    # via pronunciation-trainer
 langchain-text-splitters==0.0.1
+    # via langchain
 langsmith==0.1.56
+    # via langchain
+    # via langchain-community
+    # via langchain-core
 language-tags==1.2.0
+    # via csvw
 lxml==5.2.1
+    # via clldutils
 markdown==3.6
+    # via clldutils
 markdown-it-py==3.0.0
+    # via rich
 markupsafe==2.1.5
+    # via clldutils
+    # via gradio
+    # via jinja2
 marshmallow==3.21.2
+    # via dataclasses-json
 matplotlib==3.8.4
+    # via gradio
 mdurl==0.1.2
+    # via markdown-it-py
 mpmath==1.3.0
+    # via sympy
 multidict==6.0.5
+    # via aiohttp
+    # via yarl
 mypy-extensions==1.0.0
+    # via typing-inspect
 networkx==3.3
+    # via torch
 numpy==1.26.4
+    # via altair
+    # via contourpy
+    # via gradio
+    # via langchain
+    # via langchain-community
+    # via matplotlib
+    # via pandas
+    # via transformers
 nvidia-cublas-cu12==12.1.3.1
+    # via nvidia-cudnn-cu12
+    # via nvidia-cusolver-cu12
+    # via torch
 nvidia-cuda-cupti-cu12==12.1.105
+    # via torch
 nvidia-cuda-nvrtc-cu12==12.1.105
+    # via torch
 nvidia-cuda-runtime-cu12==12.1.105
+    # via torch
 nvidia-cudnn-cu12==8.9.2.26
+    # via torch
 nvidia-cufft-cu12==11.0.2.54
+    # via torch
 nvidia-curand-cu12==10.3.2.106
+    # via torch
 nvidia-cusolver-cu12==11.4.5.107
+    # via torch
 nvidia-cusparse-cu12==12.1.0.106
+    # via nvidia-cusolver-cu12
+    # via torch
 nvidia-nccl-cu12==2.20.5
+    # via torch
 nvidia-nvjitlink-cu12==12.4.127
+    # via nvidia-cusolver-cu12
+    # via nvidia-cusparse-cu12
 nvidia-nvtx-cu12==12.1.105
+    # via torch
 openai==1.28.0
+    # via langchain-openai
 orjson==3.10.3
+    # via fastapi
+    # via gradio
+    # via langsmith
 packaging==23.2
+    # via altair
+    # via gradio
+    # via gradio-client
+    # via huggingface-hub
+    # via langchain-core
+    # via marshmallow
+    # via matplotlib
+    # via transformers
 pandas==2.2.2
+    # via altair
+    # via gradio
 phonemizer==3.2.1
+    # via pronunciation-trainer
 pillow==10.3.0
+    # via gradio
+    # via matplotlib
 pydantic==2.7.1
+    # via fastapi
+    # via gradio
+    # via langchain
+    # via langchain-core
+    # via langsmith
+    # via openai
 pydantic-core==2.18.2
+    # via pydantic
 pydub==0.25.1
+    # via gradio
 pygments==2.18.0
+    # via rich
 pylatexenc==2.10
+    # via bibtexparser
+    # via clldutils
 pyparsing==3.1.2
+    # via matplotlib
+    # via rdflib
 python-dateutil==2.9.0.post0
+    # via clldutils
+    # via csvw
+    # via matplotlib
+    # via pandas
 python-dotenv==1.0.1
+    # via uvicorn
 python-multipart==0.0.9
+    # via fastapi
+    # via gradio
 pytz==2024.1
+    # via pandas
 pyyaml==6.0.1
+    # via gradio
+    # via huggingface-hub
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+    # via transformers
+    # via uvicorn
 rdflib==7.0.0
+    # via csvw
 referencing==0.35.1
+    # via jsonschema
+    # via jsonschema-specifications
 regex==2024.5.10
+    # via segments
+    # via tiktoken
+    # via transformers
 requests==2.31.0
+    # via csvw
+    # via huggingface-hub
+    # via langchain
+    # via langchain-community
+    # via langsmith
+    # via tiktoken
+    # via transformers
 rfc3986==1.5.0
+    # via csvw
 rich==13.7.1
+    # via typer
 rpds-py==0.18.1
+    # via jsonschema
+    # via referencing
 ruff==0.4.4
+    # via gradio
 safetensors==0.4.3
+    # via transformers
 segments==2.2.1
+    # via phonemizer
 semantic-version==2.10.0
+    # via gradio
 shellingham==1.5.4
+    # via typer
 six==1.16.0
+    # via isodate
+    # via python-dateutil
 sniffio==1.3.1
+    # via anyio
+    # via httpx
+    # via openai
 sqlalchemy==2.0.30
+    # via langchain
+    # via langchain-community
 starlette==0.37.2
+    # via fastapi
 sympy==1.12
+    # via torch
 tabulate==0.9.0
+    # via clldutils
 tenacity==8.3.0
+    # via langchain
+    # via langchain-community
+    # via langchain-core
 tiktoken==0.6.0
+    # via langchain-openai
 tokenizers==0.19.1
+    # via transformers
 tomlkit==0.12.0
+    # via gradio
 toolz==0.12.1
+    # via altair
 torch==2.3.0
+    # via pronunciation-trainer
+    # via torchaudio
 torchaudio==2.3.0
+    # via pronunciation-trainer
 tqdm==4.66.4
+    # via huggingface-hub
+    # via openai
+    # via transformers
 transformers==4.40.2
+    # via pronunciation-trainer
 triton==2.3.0
+    # via torch
 typer==0.12.3
+    # via fastapi-cli
+    # via gradio
 typing-extensions==4.11.0
+    # via altair
+    # via anyio
+    # via fastapi
+    # via gradio
+    # via gradio-client
+    # via huggingface-hub
+    # via openai
+    # via phonemizer
+    # via pydantic
+    # via pydantic-core
+    # via sqlalchemy
+    # via torch
+    # via typer
+    # via typing-inspect
+    # via uvicorn
 typing-inspect==0.9.0
+    # via dataclasses-json
 tzdata==2024.1
+    # via pandas
 ujson==5.9.0
+    # via fastapi
 uritemplate==4.1.1
+    # via csvw
 urllib3==2.2.1
+    # via gradio
+    # via requests
 uvicorn==0.29.0
+    # via fastapi
+    # via fastapi-cli
+    # via gradio
 uvloop==0.19.0
+    # via uvicorn
 watchfiles==0.21.0
+    # via uvicorn
 websockets==11.0.3
+    # via gradio-client
+    # via uvicorn
 yarl==1.9.4
-# The following packages are considered to be unsafe in a requirements file:
+    # via aiohttp
 setuptools==69.5.1
+    # via pronunciation-trainer

requirements.lock

@@ -5,143 +5,406 @@
 #   pre: false
 #   features: []
 #   all-features: false
+#   with-sources: false
 
 -e file:.
 aiofiles==23.2.1
+    # via gradio
 aiohttp==3.9.5
+    # via langchain
+    # via langchain-community
 aiosignal==1.3.1
+    # via aiohttp
 altair==5.3.0
+    # via gradio
 annotated-types==0.6.0
+    # via pydantic
 anyio==4.3.0
+    # via httpx
+    # via openai
+    # via starlette
+    # via watchfiles
+async-timeout==4.0.3
+    # via aiohttp
+    # via langchain
 attrs==23.2.0
+    # via aiohttp
+    # via clldutils
+    # via csvw
+    # via jsonschema
+    # via phonemizer
+    # via referencing
 babel==2.15.0
+    # via csvw
 bibtexparser==2.0.0b7
+    # via clldutils
 certifi==2024.2.2
+    # via httpcore
+    # via httpx
+    # via requests
 charset-normalizer==3.3.2
+    # via requests
 click==8.1.7
+    # via typer
+    # via uvicorn
 clldutils==3.22.2
+    # via segments
 colorama==0.4.6
+    # via csvw
 colorlog==6.8.2
+    # via clldutils
 contourpy==1.2.1
+    # via matplotlib
 csvw==3.3.0
+    # via segments
 cycler==0.12.1
+    # via matplotlib
 dataclasses-json==0.6.5
+    # via langchain
+    # via langchain-community
 distro==1.9.0
+    # via openai
 dlinfo==1.2.1
+    # via phonemizer
 dnspython==2.6.1
+    # via email-validator
 email-validator==2.1.1
+    # via fastapi
+exceptiongroup==1.2.1
+    # via anyio
 fastapi==0.111.0
+    # via fastapi-cli
+    # via gradio
 fastapi-cli==0.0.3
+    # via fastapi
 ffmpy==0.3.2
+    # via gradio
 filelock==3.14.0
+    # via huggingface-hub
+    # via torch
+    # via transformers
+    # via triton
 fonttools==4.51.0
+    # via matplotlib
 frozenlist==1.4.1
+    # via aiohttp
+    # via aiosignal
 fsspec==2024.3.1
+    # via gradio-client
+    # via huggingface-hub
+    # via torch
 gradio==4.29.0
+    # via pronunciation-trainer
 gradio-client==0.16.1
+    # via gradio
 greenlet==3.0.3
+    # via sqlalchemy
 h11==0.14.0
+    # via httpcore
+    # via uvicorn
 httpcore==1.0.5
+    # via httpx
 httptools==0.6.1
+    # via uvicorn
 httpx==0.27.0
+    # via fastapi
+    # via gradio
+    # via gradio-client
+    # via openai
 huggingface-hub==0.23.0
+    # via gradio
+    # via gradio-client
+    # via tokenizers
+    # via transformers
 idna==3.7
+    # via anyio
+    # via email-validator
+    # via httpx
+    # via requests
+    # via yarl
 importlib-resources==6.4.0
+    # via gradio
 isodate==0.6.1
+    # via csvw
+    # via rdflib
 jinja2==3.1.4
+    # via altair
+    # via fastapi
+    # via gradio
+    # via torch
 joblib==1.4.2
+    # via phonemizer
 jsonpatch==1.33
+    # via langchain-core
 jsonpointer==2.4
+    # via jsonpatch
 jsonschema==4.22.0
+    # via altair
+    # via csvw
 jsonschema-specifications==2023.12.1
+    # via jsonschema
 kiwisolver==1.4.5
+    # via matplotlib
 langchain==0.1.19
+    # via pronunciation-trainer
 langchain-community==0.0.38
+    # via langchain
 langchain-core==0.1.52
+    # via langchain
+    # via langchain-community
+    # via langchain-openai
+    # via langchain-text-splitters
 langchain-openai==0.1.6
+    # via pronunciation-trainer
 langchain-text-splitters==0.0.1
+    # via langchain
 langsmith==0.1.56
+    # via langchain
+    # via langchain-community
+    # via langchain-core
 language-tags==1.2.0
+    # via csvw
 lxml==5.2.1
+    # via clldutils
 markdown==3.6
+    # via clldutils
 markdown-it-py==3.0.0
+    # via rich
 markupsafe==2.1.5
+    # via clldutils
+    # via gradio
+    # via jinja2
 marshmallow==3.21.2
+    # via dataclasses-json
 matplotlib==3.8.4
+    # via gradio
 mdurl==0.1.2
+    # via markdown-it-py
 mpmath==1.3.0
+    # via sympy
 multidict==6.0.5
+    # via aiohttp
+    # via yarl
 mypy-extensions==1.0.0
+    # via typing-inspect
 networkx==3.3
+    # via torch
 numpy==1.26.4
+    # via altair
+    # via contourpy
+    # via gradio
+    # via langchain
+    # via langchain-community
+    # via matplotlib
+    # via pandas
+    # via transformers
 nvidia-cublas-cu12==12.1.3.1
+    # via nvidia-cudnn-cu12
+    # via nvidia-cusolver-cu12
+    # via torch
 nvidia-cuda-cupti-cu12==12.1.105
+    # via torch
 nvidia-cuda-nvrtc-cu12==12.1.105
+    # via torch
 nvidia-cuda-runtime-cu12==12.1.105
+    # via torch
 nvidia-cudnn-cu12==8.9.2.26
+    # via torch
 nvidia-cufft-cu12==11.0.2.54
+    # via torch
 nvidia-curand-cu12==10.3.2.106
+    # via torch
 nvidia-cusolver-cu12==11.4.5.107
+    # via torch
 nvidia-cusparse-cu12==12.1.0.106
+    # via nvidia-cusolver-cu12
+    # via torch
 nvidia-nccl-cu12==2.20.5
+    # via torch
 nvidia-nvjitlink-cu12==12.4.127
+    # via nvidia-cusolver-cu12
+    # via nvidia-cusparse-cu12
 nvidia-nvtx-cu12==12.1.105
+    # via torch
 openai==1.28.0
+    # via langchain-openai
 orjson==3.10.3
+    # via fastapi
+    # via gradio
+    # via langsmith
 packaging==23.2
+    # via altair
+    # via gradio
+    # via gradio-client
+    # via huggingface-hub
+    # via langchain-core
+    # via marshmallow
+    # via matplotlib
+    # via transformers
 pandas==2.2.2
+    # via altair
+    # via gradio
 phonemizer==3.2.1
+    # via pronunciation-trainer
 pillow==10.3.0
+    # via gradio
+    # via matplotlib
 pydantic==2.7.1
+    # via fastapi
+    # via gradio
+    # via langchain
+    # via langchain-core
+    # via langsmith
+    # via openai
 pydantic-core==2.18.2
+    # via pydantic
 pydub==0.25.1
+    # via gradio
 pygments==2.18.0
+    # via rich
 pylatexenc==2.10
+    # via bibtexparser
+    # via clldutils
 pyparsing==3.1.2
+    # via matplotlib
+    # via rdflib
 python-dateutil==2.9.0.post0
+    # via clldutils
+    # via csvw
+    # via matplotlib
+    # via pandas
 python-dotenv==1.0.1
+    # via uvicorn
 python-multipart==0.0.9
+    # via fastapi
+    # via gradio
 pytz==2024.1
+    # via pandas
 pyyaml==6.0.1
+    # via gradio
+    # via huggingface-hub
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+    # via transformers
+    # via uvicorn
 rdflib==7.0.0
+    # via csvw
 referencing==0.35.1
+    # via jsonschema
+    # via jsonschema-specifications
 regex==2024.5.10
+    # via segments
+    # via tiktoken
+    # via transformers
 requests==2.31.0
+    # via csvw
+    # via huggingface-hub
+    # via langchain
+    # via langchain-community
+    # via langsmith
+    # via tiktoken
+    # via transformers
 rfc3986==1.5.0
+    # via csvw
 rich==13.7.1
+    # via typer
 rpds-py==0.18.1
+    # via jsonschema
+    # via referencing
 ruff==0.4.4
+    # via gradio
 safetensors==0.4.3
+    # via transformers
 segments==2.2.1
+    # via phonemizer
 semantic-version==2.10.0
+    # via gradio
 shellingham==1.5.4
+    # via typer
 six==1.16.0
+    # via isodate
+    # via python-dateutil
 sniffio==1.3.1
+    # via anyio
+    # via httpx
+    # via openai
 sqlalchemy==2.0.30
+    # via langchain
+    # via langchain-community
 starlette==0.37.2
+    # via fastapi
 sympy==1.12
+    # via torch
 tabulate==0.9.0
+    # via clldutils
 tenacity==8.3.0
+    # via langchain
+    # via langchain-community
+    # via langchain-core
 tiktoken==0.6.0
+    # via langchain-openai
 tokenizers==0.19.1
+    # via transformers
 tomlkit==0.12.0
+    # via gradio
 toolz==0.12.1
+    # via altair
 torch==2.3.0
+    # via pronunciation-trainer
+    # via torchaudio
 torchaudio==2.3.0
+    # via pronunciation-trainer
 tqdm==4.66.4
+    # via huggingface-hub
+    # via openai
+    # via transformers
 transformers==4.40.2
+    # via pronunciation-trainer
 triton==2.3.0
+    # via torch
 typer==0.12.3
+    # via fastapi-cli
+    # via gradio
 typing-extensions==4.11.0
+    # via altair
+    # via anyio
+    # via fastapi
+    # via gradio
+    # via gradio-client
+    # via huggingface-hub
+    # via openai
+    # via phonemizer
+    # via pydantic
+    # via pydantic-core
+    # via sqlalchemy
+    # via torch
+    # via typer
+    # via typing-inspect
+    # via uvicorn
 typing-inspect==0.9.0
+    # via dataclasses-json
 tzdata==2024.1
+    # via pandas
 ujson==5.9.0
+    # via fastapi
 uritemplate==4.1.1
+    # via csvw
 urllib3==2.2.1
+    # via gradio
+    # via requests
 uvicorn==0.29.0
+    # via fastapi
+    # via fastapi-cli
+    # via gradio
 uvloop==0.19.0
+    # via uvicorn
 watchfiles==0.21.0
+    # via uvicorn
 websockets==11.0.3
+    # via gradio-client
+    # via uvicorn
 yarl==1.9.4
-# The following packages are considered to be unsafe in a requirements file:
+    # via aiohttp
 setuptools==69.5.1
+    # via pronunciation-trainer

src/pronunciation_trainer/evaluation.py

@@ -19,6 +19,8 @@ The advanced evaluation function includes:
 from difflib import Differ, SequenceMatcher
 from typing import Optional, Tuple
 
+import gradio as gr
+
 from pronunciation_trainer.llm import create_llm_chain
 
 
@@ -61,6 +63,18 @@ def basic_evaluation(
     expected: str, actual: str, autojunk: bool = True
 ) -> Tuple[float, str, list[Tuple[str, Optional[str]]]]:
     """Evaluate speaking attempts by comparing expected and actual phrases."""
+
+    if expected == "" or actual == "":  # If either input is empty, return 0
+        gr.Warning(
+            "To compute a similarity score, you need to supply both teacher and learner (phoneme) transcripts!"
+        )
+        return (
+            0.0,
+            """**Info:** To compute a similarity score, you need to supply both teacher and learner (phoneme) transcripts. 📝
+Simply select one of the examples on the bottom of the page or type in your own text in the textboxes above. 🖊️""",
+            [],
+        )
+
     expected, actual = normalize_texts(expected, actual)
     similarity_ratio = compare_phrases(expected, actual)
     diff = diff_phrases(expected, actual)
@@ -76,11 +90,22 @@ def advanced_evaluation(
     openai_api_key,
 ) -> str:
     """Provide LLM-based feedback"""
-    return create_llm_chain(openai_api_key=openai_api_key).invoke(
-        {
-            "learner_l1": learner_l1,
-            "learner_l2": learner_l2,
-            "learner_phoneme_transcription": learner_phoneme_transcription,
-            "teacher_phoneme_transcription": teacher_phoneme_transcription,
-        }
-    )
+    if "" in [
+        learner_l1,
+        learner_l2,
+        learner_phoneme_transcription,
+        teacher_phoneme_transcription,
+    ]:
+        gr.Warning(
+            "To compute LLM feedback, you need to supply all four inputs: learner L1, learner L2, learner phoneme transcription, and teacher phoneme transcription!"
+        )
+        return ""
+    else:
+        return create_llm_chain(openai_api_key=openai_api_key).invoke(
+            {
+                "learner_l1": learner_l1,
+                "learner_l2": learner_l2,
+                "learner_phoneme_transcription": learner_phoneme_transcription,
+                "teacher_phoneme_transcription": teacher_phoneme_transcription,
+            }
+        )