updated chunking and ui

app.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 2,
    "id": "3bedf0dc-8d8e-4ede-a9e6-b8f35136aa00",
    "metadata": {},
    "outputs": [],
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "667802a7-0f36-4136-a381-e66210b20462",
    "metadata": {},
    "outputs": [
@@ -94,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "7664bc24-e8a7-440d-851d-eb16dc2d69fb",
    "metadata": {},
    "outputs": [
@@ -128,7 +128,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "4d9863fc-969e-409b-8e20-b9c3cd2cc3e7",
    "metadata": {},
    "outputs": [],
@@ -142,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "4f486d3a",
    "metadata": {},
    "outputs": [],
@@ -187,7 +187,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "ecb7f207-0fc2-4d19-a313-356c05776832",
    "metadata": {},
    "outputs": [
@@ -208,7 +208,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
+   "id": "52d373be-3a79-412e-8ca2-92bb443fa52d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "#Number of threads created PER USER REQUEST. This throttels the # of API requests PER USER request. This is in ADDITION to the Gradio threads.\n",
+    "OPENAI_CLIENT_TTS_THREADS = 10 \n",
+    "CARTESIAAI_CLIENT_TTS_THREADS = 3\n",
+    "\n",
+    "DEFAULT_PROVIDER = 'openai'\n",
+    "DEFAULT_MODEL = 'tts-1'\n",
+    "DEFAULT_VOICE = 'alloy'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "id": "e5d6cac2-0dee-42d8-9b41-184b5be9cc3f",
    "metadata": {},
    "outputs": [],
@@ -219,7 +236,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "id": "b77ad8d6-3289-463c-b213-1c0cc215b141",
    "metadata": {},
    "outputs": [
@@ -239,6 +256,9 @@
     "        'name': 'Open AI',\n",
     "        'models': {o.id: o.id for o in openai.models.list().data if 'tts' in o.id},\n",
     "        'voices': {o:{'id':o,'name':o.title()} for o in ['alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer']},\n",
+    "        'settings': {'max_chunk_size': 4000, 'chunk_processing_time': 60, \n",
+    "                     'threads': OPENAI_CLIENT_TTS_THREADS,\n",
+    "                     'audio_file_conversion_kwargs':{'format': 'mp3'}},\n",
     "    }\n",
     "    print('Successfully added OpenAI as Provider')\n",
     "except Exception as e:\n",
@@ -248,7 +268,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 11,
    "id": "87fca48b-a16a-4d2b-919c-75e88e4e5eb5",
    "metadata": {},
    "outputs": [
@@ -268,6 +288,10 @@
     "        'name': 'Cartesia AI',\n",
     "        'models': {'upbeat-moon': 'Sonic Turbo English'},\n",
     "        'voices': {v['id']:v for k,v in cartesia.tts.CartesiaTTS().get_voices().items()},\n",
+    "        'settings': {'max_chunk_size': 500, 'chunk_processing_time': 20, \n",
+    "                     'threads': CARTESIAAI_CLIENT_TTS_THREADS,\n",
+    "                     'audio_file_conversion_kwargs':{'format': 'raw', 'frame_rate': 44100, \n",
+    "                                                     'channels': 1, 'sample_width': 2}},\n",
     "    }\n",
     "    print('Successfully added Cartesia AI as Provider')\n",
     "except Exception as e:\n",
@@ -316,30 +340,62 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "8eb7e7d5-7121-4762-b8d1-e5a9539e2b36",
+   "execution_count": 12,
+   "id": "d1352f28-f761-4e91-a9bc-4efe47552f4d",
    "metadata": {},
    "outputs": [],
    "source": [
-    "#| export\n",
-    "clean_text_prompt = \"\"\"Your job is to clean up text that is going to be fed into a text to speech (TTS) model. You must remove parts of the text that would not normally be spoken such as reference marks `[1]`, spurious citations such as `(Reddy et al., 2021; Wu et al., 2022; Chang et al., 2022; Kondratyuk et al., 2023)` and any other part of the text that is not normally spoken. Please also clean up sections and headers so they are on new lines with proper numbering. You must also clean up any math formulas that are salvageable from being copied from a scientific paper. If they are garbled and do not make sense then remove them. You must carefully perform the text cleanup so it is translated into speech that is easy to listen to however you must not modify the text otherwise. It is critical that you repeat all of the text without modifications except for the cleanup activities you've been instructed to do. Also you must clean all of the text you are given, you may not omit any of it or stop the cleanup task early.\"\"\"\n"
+    "# {v['id']:v['name'] for k,v in cartesia.tts.CartesiaTTS().get_voices().items()},"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a06e16b3-6310-462e-8192-b65ca324d86f",
+   "metadata": {},
+   "source": [
+    "```\n",
+    "({'3b554273-4299-48b9-9aaf-eefd438e3941': 'Indian Lady',\n",
+    "  '63ff761f-c1e8-414b-b969-d1833d1c870c': 'Confident British Man',\n",
+    "  'daf747c6-6bc2-4083-bd59-aa94dce23f5d': 'Middle Eastern Woman',\n",
+    "  'ed81fd13-2016-4a49-8fe3-c0d2761695fc': 'Sportsman',\n",
+    "  'f114a467-c40a-4db8-964d-aaba89cd08fa': 'Yogaman',\n",
+    "  'c45bc5ec-dc68-4feb-8829-6e6b2748095d': 'Movieman',\n",
+    "  '87748186-23bb-4158-a1eb-332911b0b708': 'Wizardman',\n",
+    "  '98a34ef2-2140-4c28-9c71-663dc4dd7022': 'Southern Man',\n",
+    "  '79f8b5fb-2cc8-479a-80df-29f7a7cf1a3e': 'Nonfiction Man',\n",
+    "  '36b42fcb-60c5-4bec-b077-cb1a00a92ec6': 'Pilot over Intercom',\n",
+    "  '69267136-1bdc-412f-ad78-0caad210fb40': 'Friendly Reading Man',\n",
+    "  '15a9cd88-84b0-4a8b-95f2-5d583b54c72e': 'Reading Lady',\n",
+    "  '95856005-0332-41b0-935f-352e296aa0df': 'Classy British Man',\n",
+    "  'd46abd1d-2d02-43e8-819f-51fb652c1c61': 'Newsman',\n",
+    "  '2ee87190-8f84-4925-97da-e52547f9462c': 'Child',\n",
+    "  'c2ac25f9-ecc4-4f56-9095-651354df60c0': 'Commercial Lady',\n",
+    "  '5345cf08-6f37-424d-a5d9-8ae1101b9377': 'Maria',\n",
+    "  'a3520a8f-226a-428d-9fcd-b0a4711a6829': 'Reflective Woman',\n",
+    "  'e3827ec5-697a-4b7c-9704-1a23041bbc51': 'Sweet Lady',\n",
+    "  'a0e99841-438c-4a64-b679-ae501e7d6091': 'Barbershop Man',\n",
+    "  'cd17ff2d-5ea4-4695-be8f-42193949b946': 'Meditation Lady',\n",
+    "  'bf991597-6c13-47e4-8411-91ec2de5c466': 'Newslady',\n",
+    "  '41534e16-2966-4c6b-9670-111411def906': \"1920's Radioman\",\n",
+    "  '79a125e8-cd45-4c13-8a67-188112f4dd22': 'British Lady',\n",
+    "  'a167e0f3-df7e-4d52-a9c3-f949145efdab': 'Ted',\n",
+    "  '248be419-c632-4f23-adf1-5324ed7dbf1d': 'Hannah',\n",
+    "  'c8605446-247c-4d39-acd4-8f4c28aa363c': 'Wise Lady',\n",
+    "  '00a77add-48d5-4ef6-8157-71e5437b282d': 'Calm Lady',\n",
+    "  '638efaaa-4d0c-442e-b701-3fae16aad012': 'Indian Man',\n",
+    "  'd6b6d712-6030-4420-9771-8b35f326fd20': 'Mat 1'},)\n",
+    "```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "52d373be-3a79-412e-8ca2-92bb443fa52d",
+   "execution_count": 13,
+   "id": "8eb7e7d5-7121-4762-b8d1-e5a9539e2b36",
    "metadata": {},
    "outputs": [],
    "source": [
     "#| export\n",
-    "#Number of threads created PER USER REQUEST. This throttels the # of API requests PER USER request. This is in ADDITION to the Gradio threads.\n",
-    "OPENAI_CLIENT_TTS_THREADS = 10 \n",
-    "CARTESIAAI_CLIENT_TTS_THREADS = 3\n",
-    "\n",
-    "DEFAULT_PROVIDER = 'openai'\n",
-    "DEFAULT_MODEL = 'tts-1'\n",
-    "DEFAULT_VOICE = 'alloy'"
+    "clean_text_prompt = \"\"\"Your job is to clean up text that is going to be fed into a text to speech (TTS) model. You must remove parts of the text that would not normally be spoken such as reference marks `[1]`, spurious citations such as `(Reddy et al., 2021; Wu et al., 2022; Chang et al., 2022; Kondratyuk et al., 2023)` and any other part of the text that is not normally spoken. Please also clean up sections and headers so they are on new lines with proper numbering. You must also clean up any math formulas that are salvageable from being copied from a scientific paper. If they are garbled and do not make sense then remove them. You must carefully perform the text cleanup so it is translated into speech that is easy to listen to however you must not modify the text otherwise. It is critical that you repeat all of the text without modifications except for the cleanup activities you've been instructed to do. Also you must clean all of the text you are given, you may not omit any of it or stop the cleanup task early.\"\"\"\n"
    ]
   },
   {
@@ -352,7 +408,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 14,
    "id": "b5b29507-92bc-453d-bcc5-6402c17e9a0d",
    "metadata": {},
    "outputs": [],
@@ -372,13 +428,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 15,
    "id": "24674094-4d47-4e48-b591-55faabcff8df",
    "metadata": {},
    "outputs": [],
    "source": [
     "#| export\n",
-    "def split_text(input_text, max_length=4000, lookback=1000):\n",
+    "def split_text(input_text, provider):\n",
+    "    settings = providers[provider]['settings']\n",
+    "    max_length = settings['max_chunk_size']\n",
+    "    lookback = max_length // 4\n",
+    "        \n",
     "    # If the text is shorter than the max_length, return it as is\n",
     "    if len(input_text) <= max_length:\n",
     "        return [input_text]\n",
@@ -413,7 +473,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 16,
    "id": "e6224ae5-3792-42b2-8392-3abd42998a50",
    "metadata": {},
    "outputs": [],
@@ -452,10 +512,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 17,
    "id": "4691703d-ed0f-4481-8006-b2906289b780",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Added create_speech_func for openai provider\n"
+     ]
+    }
+   ],
    "source": [
     "#| export\n",
     "def create_speech_openai(chunk_idx, input, model='tts-1', voice='alloy', speed=1.0, **kwargs):\n",
@@ -467,7 +535,10 @@
     "    \n",
     "    response = _create_speech_with_backoff(input=input, model=model, voice=voice, speed=speed, **kwargs)\n",
     "    client.close()\n",
-    "    return chunk_idx, response.content"
+    "    return chunk_idx, response.content\n",
+    "if 'openai' in providers.keys():\n",
+    "    providers['openai']['settings']['create_speech_func'] = create_speech_openai\n",
+    "    print('Added create_speech_func for openai provider')"
    ]
   },
   {
@@ -504,10 +575,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 18,
    "id": "3420c868-71cb-4ac6-ac65-6f02bfd841d1",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Added create_speech_func for create_speech_cartesiaai provider\n"
+     ]
+    }
+   ],
    "source": [
     "#| export\n",
     "def create_speech_cartesiaai(chunk_idx, input, model='upbeat-moon', \n",
@@ -527,54 +606,68 @@
     "                                           output_format=output_format, \n",
     "                                           **kwargs)\n",
     "    client.close()\n",
-    "    return chunk_idx, response[\"audio\"]"
+    "    return chunk_idx, response[\"audio\"]\n",
+    "if 'cartesiaai' in providers.keys():\n",
+    "    providers['cartesiaai']['settings']['create_speech_func'] = create_speech_cartesiaai\n",
+    "    print('Added create_speech_func for create_speech_cartesiaai provider')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 19,
    "id": "d0082383-9d03-4b25-b68a-080d0b28caa9",
    "metadata": {},
    "outputs": [],
    "source": [
     "# test\n",
     "# create_speech_cartesiaai(1,\"Hi. What's your name?\", model='upbeat-moon',\n",
-    "#               voice='63ff761f-c1e8-414b-b969-d1833d1c870c')"
+    "#               voice='63ff761f-c1e8-414b-b969-d1833d1c870c')\n",
+    "# text = \"\"\"Ladies and Gentlemen, gather 'round your radio sets for a special report on a remarkable phenomenon sweeping the nation! It seems a new generation of prodigies is lighting up our schools and captivating communities from coast to coast. Yes, we're talking about gifted children, those bright young minds whose talents and intellects are far beyond their tender years.\n",
+    "# In classrooms across the country, educators are reporting an unprecedented wave of exceptional youngsters. These gifted children, some as young as five or six, are astonishing their teachers with feats of arithmetic, literacy, and creativity that rival those of much older students. The age of enlightenment is upon us, and it starts with these brilliant boys and girls!\n",
+    "# Take young Tommy Caldwell of Newark, New Jersey, for instance. At the ripe age of seven, Tommy has already mastered algebra and is now diving into the wonders of geometry. His teacher, Miss Grace Whittaker, says she’s never seen such a gifted mathematician in her twenty years of teaching. And Tommy is just one of many!\n",
+    "# Then there's little Sally Henderson of Topeka, Kansas. At the tender age of eight, Sally has penned her first book of poetry, a collection that has local literary circles abuzz with excitement. Her vivid imagination and eloquent verse have earned her the nickname “The Young Bard of Topeka.” The town is swelling with pride for their young poetess.\n",
+    "# Experts from esteemed institutions like Harvard and Yale are paying close attention to this trend, conducting studies to understand the roots of such exceptional abilities. Some suggest it’s the result of improved nutrition and health care, while others believe it’s the progressive educational methods now being employed in our schools. Regardless of the cause, one thing is clear: America is home to a new generation of geniuses!\n",
+    "# Communities are rallying to support these young prodigies, with special programs and schools being established to nurture their extraordinary talents. Parents, teachers, and civic leaders are united in their mission to provide the resources and opportunities these gifted children need to reach their full potential.\n",
+    "# So, dear listeners, as you sit by your radios tonight, take heart in the knowledge that our future is bright. With these remarkable young minds leading the way, the possibilities are endless. This is your announcer signing off, wishing you all a splendid evening and a hopeful tomorrow.\"\"\"\n",
+    "# _, test_data = create_speech_cartesiaai(1, text, model='upbeat-moon',\n",
+    "#               voice='41534e16-2966-4c6b-9670-111411def906')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 20,
+   "id": "649d90a5-9398-4cb5-a1e8-a464d463a11c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# test_file = AudioSegment.from_file(io.BytesIO(test_data), **{'format': 'raw', 'frame_rate': 44100, 'channels': 1, 'sample_width': 2})\n",
+    "# test_file.export('./test3.mp3', format=\"mp3\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
    "id": "e34bb4aa-698c-4452-8cda-bd02b38f7122",
    "metadata": {},
    "outputs": [],
    "source": [
     "#| export\n",
     "def create_speech(input_text, provider, model='tts-1', voice='alloy', \n",
-    "                  profile: gr.OAuthProfile|None=None, \n",
+    "                  profile: gr.OAuthProfile|None=None, # comment out of running locally\n",
     "                  progress=gr.Progress(), **kwargs):\n",
     "\n",
     "    #Verify auth if it is required. This is very important if this is in a HF space. DO NOT DELETE!!!\n",
     "    if REQUIRE_AUTH: verify_authorization(profile)\n",
     "    start = datetime.now()\n",
     "    \n",
-    "    if provider == 'cartesiaai':\n",
-    "        create_speech_func = create_speech_cartesiaai\n",
-    "        max_chunk_size = 500\n",
-    "        chunk_processing_time = 20\n",
-    "        threads = CARTESIAAI_CLIENT_TTS_THREADS\n",
-    "        audio_file_conversion_kwargs = {'format': 'raw', 'frame_rate': 44100, 'channels': 1, 'sample_width': 2}\n",
-    "    elif provider == 'openai':\n",
-    "        create_speech_func = create_speech_openai\n",
-    "        max_chunk_size = 4000\n",
-    "        chunk_processing_time = 60\n",
-    "        threads = OPENAI_CLIENT_TTS_THREADS\n",
-    "        audio_file_conversion_kwargs = {'format': 'mp3'}\n",
-    "    else:\n",
-    "        raise ValueError(f'Invalid argument provider: {provider}')\n",
+    "    settings = providers[provider]['settings']\n",
+    "    create_speech_func = settings['create_speech_func']\n",
+    "    chunk_processing_time = settings['chunk_processing_time']\n",
+    "    threads = settings['threads']\n",
+    "    audio_file_conversion_kwargs = settings['audio_file_conversion_kwargs']\n",
     "    \n",
     "    # Split the input text into chunks\n",
-    "    chunks = split_text(input_text, max_length=max_chunk_size)\n",
+    "    chunks = split_text(input_text, provider=provider)\n",
     "\n",
     "    # Initialize the progress bar\n",
     "    progress(0, desc=f\"Started processing {len(chunks)} text chunks using {threads} threads. ETA is ~{ceil(len(chunks)/threads)*chunk_processing_time/60.} min.\")\n",
@@ -606,7 +699,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 22,
    "id": "ca2c6f8c-62ed-4ac1-9c2f-e3b2bfb47e8d",
    "metadata": {},
    "outputs": [],
@@ -618,7 +711,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 23,
    "id": "236dd8d3-4364-4731-af93-7dcdec6f18a1",
    "metadata": {},
    "outputs": [],
@@ -630,7 +723,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 24,
    "id": "0523a158-ee07-48b3-9350-ee39d4deee7f",
    "metadata": {},
    "outputs": [],
@@ -652,7 +745,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 25,
    "id": "f4d1ba0b-6960-4e22-8dba-7de70370753a",
    "metadata": {},
    "outputs": [],
@@ -664,7 +757,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 26,
    "id": "efa28cf2-548d-439f-bf2a-21a5edbf9eba",
    "metadata": {},
    "outputs": [],
@@ -677,7 +770,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 27,
    "id": "cdc1dde5-5edd-4dbf-bd11-30eb418c571d",
    "metadata": {},
    "outputs": [],
@@ -689,7 +782,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 28,
    "id": "035c33dd-c8e6-42b4-91d4-6bc5f1b36df3",
    "metadata": {},
    "outputs": [],
@@ -702,13 +795,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 29,
+   "id": "c97c03af-a377-42e1-93e0-1df957c0e4cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def split_text_as_md(*args, **kwargs):\n",
+    "    output = split_text(*args, **kwargs)\n",
+    "    return '# Text Splits:\\n' + '<br>----------<br>'.join(output)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
    "id": "e4fb3159-579b-4271-bc96-4cd1e2816eca",
    "metadata": {},
    "outputs": [],
    "source": [
     "#| export\n",
     "with gr.Blocks(title='TTS', head='TTS', delete_cache=(3600,3600)) as app:\n",
+    "    \n",
+    "    ### Define UI ###\n",
     "    gr.Markdown(\"# TTS\")\n",
     "    gr.Markdown(\"\"\"Start typing below and then click **Go** to create the speech from your text.\n",
     "For requests longer than allowed by the API they will be broken into chunks automatically. [Spaces Link](https://matdmiller-tts-openai.hf.space/) | <a href=\"https://matdmiller-tts-openai.hf.space/\" target=\"_blank\">Spaces Link HTML</a>\"\"\")\n",
@@ -725,39 +832,52 @@
     "        generation_cost = gr.Label(label=\"Generation cost\")\n",
     "    with gr.Row():\n",
     "        output_audio = gr.Audio()\n",
+    "    go_btn = gr.Button(\"Go\")\n",
+    "    clear_btn = gr.Button('Clear')\n",
+    "    if REQUIRE_AUTH:\n",
+    "        gr.LoginButton()\n",
+    "        auth_md = gr.Markdown('')\n",
+    "        \n",
+    "    chunks_md = gr.Markdown('',label='Chunks')\n",
+    "    \n",
     "\n",
-    "    #input_text \n",
+    "    ### Define UI Actions ###\n",
+    "    \n",
+    "    # input_text \n",
     "    input_text.input(fn=get_input_text_len, inputs=input_text, outputs=input_text_length)\n",
     "    input_text.input(fn=get_generation_cost, \n",
     "                     inputs=[input_text,tts_model_dropdown,tts_provider_dropdown], \n",
     "                     outputs=generation_cost)\n",
-    "\n",
+    "    input_text.input(fn=split_text_as_md, inputs=[input_text,tts_provider_dropdown], outputs=chunks_md)\n",
+    "    \n",
+    "    # tts_provider_dropdown\n",
     "    tts_provider_dropdown.change(fn=update_model_choices, inputs=[tts_provider_dropdown], \n",
     "                                 outputs=tts_model_dropdown)\n",
     "    tts_provider_dropdown.change(fn=update_voice_choices, inputs=[tts_provider_dropdown, tts_model_dropdown], \n",
     "                                 outputs=tts_voice_dropdown)\n",
+    "    tts_provider_dropdown.change(fn=split_text_as_md, inputs=[input_text,tts_provider_dropdown], outputs=chunks_md)\n",
     "    \n",
+    "    # tts_model_dropdown\n",
     "    tts_model_dropdown.change(fn=get_generation_cost, \n",
     "                              inputs=[input_text,tts_model_dropdown,tts_provider_dropdown], outputs=generation_cost)\n",
     "    \n",
-    "    go_btn = gr.Button(\"Go\")\n",
+    "    \n",
     "    go_btn.click(fn=create_speech, \n",
     "                 inputs=[input_text, tts_provider_dropdown, tts_model_dropdown, tts_voice_dropdown], \n",
     "                 outputs=[output_audio])\n",
     "    \n",
-    "    clear_btn = gr.Button('Clear')\n",
+    "    \n",
     "    clear_btn.click(fn=lambda: '', outputs=input_text)\n",
     "\n",
     "    if REQUIRE_AUTH:\n",
-    "        gr.LoginButton()\n",
-    "        m = gr.Markdown('')\n",
-    "        app.load(verify_authorization, None, m)\n",
+    "        app.load(verify_authorization, None, auth_md)\n",
+    "    \n",
     "    "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 31,
    "id": "a00648a1-891b-470b-9959-f5d502055713",
    "metadata": {},
    "outputs": [],
@@ -771,7 +891,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 32,
    "id": "4b534fe7-4337-423e-846a-1bdb7cccc4ea",
    "metadata": {},
    "outputs": [
@@ -779,7 +899,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7861\n",
+      "Running on local URL:  http://127.0.0.1:7860\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -787,7 +907,7 @@
     {
      "data": {
       "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7861/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -800,7 +920,7 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 28,
+     "execution_count": 32,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -828,7 +948,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 33,
    "id": "28e8d888-e790-46fa-bbac-4511b9ab796c",
    "metadata": {},
    "outputs": [
@@ -836,7 +956,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Closing server running on port: 7861\n"
+      "Closing server running on port: 7860\n"
      ]
     }
    ],
@@ -847,7 +967,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": null,
    "id": "afbc9699-4d16-4060-88f4-cd1251754cbd",
    "metadata": {},
    "outputs": [],
@@ -858,7 +978,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": null,
    "id": "0420310d-930b-4904-8bd4-3458ad8bdbd3",
    "metadata": {},
    "outputs": [],

app.py

@@ -1,8 +1,8 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: app.ipynb.
 
 # %% auto 0
-__all__ = ['secret_import_failed', 'TEMP', 'TEMP_DIR', 'providers', 'clean_text_prompt', 'OPENAI_CLIENT_TTS_THREADS',
-           'CARTESIAAI_CLIENT_TTS_THREADS', 'DEFAULT_PROVIDER', 'DEFAULT_MODEL', 'DEFAULT_VOICE', 'launch_kwargs',
+__all__ = ['secret_import_failed', 'TEMP', 'TEMP_DIR', 'OPENAI_CLIENT_TTS_THREADS', 'CARTESIAAI_CLIENT_TTS_THREADS',
+           'DEFAULT_PROVIDER', 'DEFAULT_MODEL', 'DEFAULT_VOICE', 'providers', 'clean_text_prompt', 'launch_kwargs',
            'queue_kwargs', 'verify_authorization', 'split_text', 'concatenate_audio', 'create_speech_openai',
            'create_speech_cartesiaai', 'create_speech', 'get_input_text_len', 'get_generation_cost',
            'get_model_choices', 'update_model_choices', 'get_voice_choices', 'update_voice_choices']
@@ -76,48 +76,55 @@ TEMP_DIR = Path(TEMP)
 print('TEMP Dir:', TEMP_DIR)
 
 # %% app.ipynb 12
-providers = dict()
+#Number of threads created PER USER REQUEST. This throttels the # of API requests PER USER request. This is in ADDITION to the Gradio threads.
+OPENAI_CLIENT_TTS_THREADS = 10 
+CARTESIAAI_CLIENT_TTS_THREADS = 3
+
+DEFAULT_PROVIDER = 'openai'
+DEFAULT_MODEL = 'tts-1'
+DEFAULT_VOICE = 'alloy'
 
 # %% app.ipynb 13
+providers = dict()
+
+# %% app.ipynb 14
 # Add OpenAI as a provider
 try:
     providers['openai'] = {
         'name': 'Open AI',
         'models': {o.id: o.id for o in openai.models.list().data if 'tts' in o.id},
         'voices': {o:{'id':o,'name':o.title()} for o in ['alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer']},
+        'settings': {'max_chunk_size': 4000, 'chunk_processing_time': 60, 
+                     'threads': OPENAI_CLIENT_TTS_THREADS,
+                     'audio_file_conversion_kwargs':{'format': 'mp3'}},
     }
     print('Successfully added OpenAI as Provider')
 except Exception as e:
     print(f"""Error: Failed to add OpenAI as a provider.\nException: {repr(e)}\nTRACEBACK:\n""",traceback.format_exc())
 # providers
 
-# %% app.ipynb 14
+# %% app.ipynb 15
 # Add Cartesia AI as a provider
 try:
     providers['cartesiaai'] = {
         'name': 'Cartesia AI',
         'models': {'upbeat-moon': 'Sonic Turbo English'},
         'voices': {v['id']:v for k,v in cartesia.tts.CartesiaTTS().get_voices().items()},
+        'settings': {'max_chunk_size': 500, 'chunk_processing_time': 20, 
+                     'threads': CARTESIAAI_CLIENT_TTS_THREADS,
+                     'audio_file_conversion_kwargs':{'format': 'raw', 'frame_rate': 44100, 
+                                                     'channels': 1, 'sample_width': 2}},
     }
     print('Successfully added Cartesia AI as Provider')
 except Exception as e:
     print(f"""Error: Failed to add Cartesia AI as a provider.\nException: {repr(e)}\nTRACEBACK:\n""",traceback.format_exc())
 # providers
 
-# %% app.ipynb 16
+# %% app.ipynb 19
 clean_text_prompt = """Your job is to clean up text that is going to be fed into a text to speech (TTS) model. You must remove parts of the text that would not normally be spoken such as reference marks `[1]`, spurious citations such as `(Reddy et al., 2021; Wu et al., 2022; Chang et al., 2022; Kondratyuk et al., 2023)` and any other part of the text that is not normally spoken. Please also clean up sections and headers so they are on new lines with proper numbering. You must also clean up any math formulas that are salvageable from being copied from a scientific paper. If they are garbled and do not make sense then remove them. You must carefully perform the text cleanup so it is translated into speech that is easy to listen to however you must not modify the text otherwise. It is critical that you repeat all of the text without modifications except for the cleanup activities you've been instructed to do. Also you must clean all of the text you are given, you may not omit any of it or stop the cleanup task early."""
 
 
-# %% app.ipynb 17
-#Number of threads created PER USER REQUEST. This throttels the # of API requests PER USER request. This is in ADDITION to the Gradio threads.
-OPENAI_CLIENT_TTS_THREADS = 10 
-CARTESIAAI_CLIENT_TTS_THREADS = 3
-
-DEFAULT_PROVIDER = 'openai'
-DEFAULT_MODEL = 'tts-1'
-DEFAULT_VOICE = 'alloy'
-
-# %% app.ipynb 19
+# %% app.ipynb 21
 def verify_authorization(profile: gr.OAuthProfile=None) -> str:
     print('Profile:', profile)
     if REQUIRE_AUTH == False:
@@ -129,8 +136,12 @@ def verify_authorization(profile: gr.OAuthProfile=None) -> str:
         raise PermissionError(f'Your huggingface username ({profile}) is not authorized. Must be set in ALLOWED_OAUTH_PROFILE_USERNAMES environment variable.')
         return None
 
-# %% app.ipynb 20
-def split_text(input_text, max_length=4000, lookback=1000):
+# %% app.ipynb 22
+def split_text(input_text, provider):
+    settings = providers[provider]['settings']
+    max_length = settings['max_chunk_size']
+    lookback = max_length // 4
+        
     # If the text is shorter than the max_length, return it as is
     if len(input_text) <= max_length:
         return [input_text]
@@ -162,7 +173,7 @@ def split_text(input_text, max_length=4000, lookback=1000):
 
     return chunks
 
-# %% app.ipynb 21
+# %% app.ipynb 23
 def concatenate_audio(files:list, **kwargs):
 
     # Initialize an empty AudioSegment object for concatenation
@@ -193,7 +204,7 @@ def concatenate_audio(files:list, **kwargs):
     print('Saving mp3 file to temp directory: ', filepath)
     return str(filepath)
 
-# %% app.ipynb 22
+# %% app.ipynb 24
 def create_speech_openai(chunk_idx, input, model='tts-1', voice='alloy', speed=1.0, **kwargs):
     client = openai.OpenAI()
     
@@ -204,8 +215,11 @@ def create_speech_openai(chunk_idx, input, model='tts-1', voice='alloy', speed=1
     response = _create_speech_with_backoff(input=input, model=model, voice=voice, speed=speed, **kwargs)
     client.close()
     return chunk_idx, response.content
+if 'openai' in providers.keys():
+    providers['openai']['settings']['create_speech_func'] = create_speech_openai
+    print('Added create_speech_func for openai provider')
 
-# %% app.ipynb 24
+# %% app.ipynb 26
 def create_speech_cartesiaai(chunk_idx, input, model='upbeat-moon', 
                              voice='248be419-c632-4f23-adf1-5324ed7dbf1d', #Hannah
                              websocket=False, 
@@ -224,33 +238,27 @@ def create_speech_cartesiaai(chunk_idx, input, model='upbeat-moon',
                                            **kwargs)
     client.close()
     return chunk_idx, response["audio"]
+if 'cartesiaai' in providers.keys():
+    providers['cartesiaai']['settings']['create_speech_func'] = create_speech_cartesiaai
+    print('Added create_speech_func for create_speech_cartesiaai provider')
 
-# %% app.ipynb 26
+# %% app.ipynb 29
 def create_speech(input_text, provider, model='tts-1', voice='alloy', 
-                  profile: gr.OAuthProfile|None=None, 
+                  profile: gr.OAuthProfile|None=None, # comment out of running locally
                   progress=gr.Progress(), **kwargs):
 
     #Verify auth if it is required. This is very important if this is in a HF space. DO NOT DELETE!!!
     if REQUIRE_AUTH: verify_authorization(profile)
     start = datetime.now()
     
-    if provider == 'cartesiaai':
-        create_speech_func = create_speech_cartesiaai
-        max_chunk_size = 500
-        chunk_processing_time = 20
-        threads = CARTESIAAI_CLIENT_TTS_THREADS
-        audio_file_conversion_kwargs = {'format': 'raw', 'frame_rate': 44100, 'channels': 1, 'sample_width': 2}
-    elif provider == 'openai':
-        create_speech_func = create_speech_openai
-        max_chunk_size = 4000
-        chunk_processing_time = 60
-        threads = OPENAI_CLIENT_TTS_THREADS
-        audio_file_conversion_kwargs = {'format': 'mp3'}
-    else:
-        raise ValueError(f'Invalid argument provider: {provider}')
+    settings = providers[provider]['settings']
+    create_speech_func = settings['create_speech_func']
+    chunk_processing_time = settings['chunk_processing_time']
+    threads = settings['threads']
+    audio_file_conversion_kwargs = settings['audio_file_conversion_kwargs']
     
     # Split the input text into chunks
-    chunks = split_text(input_text, max_length=max_chunk_size)
+    chunks = split_text(input_text, provider=provider)
 
     # Initialize the progress bar
     progress(0, desc=f"Started processing {len(chunks)} text chunks using {threads} threads. ETA is ~{ceil(len(chunks)/threads)*chunk_processing_time/60.} min.")
@@ -280,11 +288,11 @@ def create_speech(input_text, provider, model='tts-1', voice='alloy',
     return combined_audio
 
 
-# %% app.ipynb 28
+# %% app.ipynb 31
 def get_input_text_len(input_text):
     return len(input_text)
 
-# %% app.ipynb 29
+# %% app.ipynb 32
 def get_generation_cost(input_text, tts_model_dropdown, provider):
     text_len = len(input_text)
     if provider == 'openai':
@@ -298,26 +306,28 @@ def get_generation_cost(input_text, tts_model_dropdown, provider):
         raise ValueError(f'Invalid argument provider: {provider}')
     return "${:,.3f}".format(cost)
 
-# %% app.ipynb 30
+# %% app.ipynb 33
 def get_model_choices(provider):
     return sorted([(v,k) for k,v in providers[provider]['models'].items()])
 
-# %% app.ipynb 31
+# %% app.ipynb 34
 def update_model_choices(provider):
     choices = get_model_choices(provider)
     return gr.update(choices=choices,value=choices[0][1])
 
-# %% app.ipynb 32
+# %% app.ipynb 35
 def get_voice_choices(provider, model):
     return sorted([(v['name'],v['id']) for v in providers[provider]['voices'].values()])
 
-# %% app.ipynb 33
+# %% app.ipynb 36
 def update_voice_choices(provider, model):
     choices = get_voice_choices(provider, model)
     return gr.update(choices=choices,value=choices[0][1])
 
-# %% app.ipynb 34
+# %% app.ipynb 38
 with gr.Blocks(title='TTS', head='TTS', delete_cache=(3600,3600)) as app:
+    
+    ### Define UI ###
     gr.Markdown("# TTS")
     gr.Markdown("""Start typing below and then click **Go** to create the speech from your text.
 For requests longer than allowed by the API they will be broken into chunks automatically. [Spaces Link](https://matdmiller-tts-openai.hf.space/) | <a href="https://matdmiller-tts-openai.hf.space/" target="_blank">Spaces Link HTML</a>""")
@@ -334,42 +344,55 @@ For requests longer than allowed by the API they will be broken into chunks auto
         generation_cost = gr.Label(label="Generation cost")
     with gr.Row():
         output_audio = gr.Audio()
+    go_btn = gr.Button("Go")
+    clear_btn = gr.Button('Clear')
+    if REQUIRE_AUTH:
+        gr.LoginButton()
+        auth_md = gr.Markdown('')
+        
+    chunks_md = gr.Markdown('',label='Chunks')
+    
 
-    #input_text 
+    ### Define UI Actions ###
+    
+    # input_text 
     input_text.input(fn=get_input_text_len, inputs=input_text, outputs=input_text_length)
     input_text.input(fn=get_generation_cost, 
                      inputs=[input_text,tts_model_dropdown,tts_provider_dropdown], 
                      outputs=generation_cost)
-
+    input_text.input(fn=split_text_as_md, inputs=[input_text,tts_provider_dropdown], outputs=chunks_md)
+    
+    # tts_provider_dropdown
     tts_provider_dropdown.change(fn=update_model_choices, inputs=[tts_provider_dropdown], 
                                  outputs=tts_model_dropdown)
     tts_provider_dropdown.change(fn=update_voice_choices, inputs=[tts_provider_dropdown, tts_model_dropdown], 
                                  outputs=tts_voice_dropdown)
+    tts_provider_dropdown.change(fn=split_text_as_md, inputs=[input_text,tts_provider_dropdown], outputs=chunks_md)
     
+    # tts_model_dropdown
     tts_model_dropdown.change(fn=get_generation_cost, 
                               inputs=[input_text,tts_model_dropdown,tts_provider_dropdown], outputs=generation_cost)
     
-    go_btn = gr.Button("Go")
+    
     go_btn.click(fn=create_speech, 
                  inputs=[input_text, tts_provider_dropdown, tts_model_dropdown, tts_voice_dropdown], 
                  outputs=[output_audio])
     
-    clear_btn = gr.Button('Clear')
+    
     clear_btn.click(fn=lambda: '', outputs=input_text)
 
     if REQUIRE_AUTH:
-        gr.LoginButton()
-        m = gr.Markdown('')
-        app.load(verify_authorization, None, m)
+        app.load(verify_authorization, None, auth_md)
+    
     
 
-# %% app.ipynb 35
+# %% app.ipynb 39
 # launch_kwargs = {'auth':('username',GRADIO_PASSWORD),
 #                  'auth_message':'Please log in to Mat\'s TTS App with username: username and password.'}
 launch_kwargs = {}
 queue_kwargs = {'default_concurrency_limit':10}
 
-# %% app.ipynb 37
+# %% app.ipynb 41
 #.py launch
 if __name__ == "__main__":
     app.queue(**queue_kwargs)