Upload 2 files

README.md

@@ -10,10 +10,13 @@ pipeline_tag: text-to-speech
 
 ✨ You can now [`pip install kokoro`](https://github.com/hexgrad/kokoro)! See [Usage](https://huggingface.co/hexgrad/Kokoro-82M#usage).
 
+<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/HEARME.wav" type="audio/wav"></audio>
+
 **Kokoro** is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects.
 
 - [Releases](#releases)
 - [Usage](#usage)
+- [SAMPLES.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/SAMPLES.md) ↗️
 - [VOICES.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) ↗️
 - [Model Facts](#model-facts)
 - [Training Details](#training-details)
@@ -24,14 +27,14 @@ pipeline_tag: text-to-speech
 
 | Model | Published | Training Data | Compute (A100 80GB) | Langs & Voices | SHA256 |
 | ----- | --------- | ------------- | ------------------- | -------------- | ------ |
-| **v1.0** | **2025 Jan 27** | **Few hundred hrs** | **$1000 for 1000 hrs** | [**8 & 53**](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) | `496dba11` |
+| **v1.0** | **2025 Jan 27** | **Few hundred hrs** | **$1000 for 1000 hrs** | [**8 & 54**](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) | `496dba11` |
 | [v0.19](https://huggingface.co/hexgrad/kLegacy/tree/main/v0.19) | 2024 Dec 25 | <100 hrs | $400 for 500 hrs | 1 & 10 | `3b0c392f` |
 
 ### Usage
 
 [`pip install kokoro`](https://pypi.org/project/kokoro/) installs the inference library at https://github.com/hexgrad/kokoro
 
-You can run this cell on [Google Colab](https://colab.research.google.com/).
+You can run this cell on [Google Colab](https://colab.research.google.com/). [Listen to samples](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/SAMPLES.md).
 ```py
 # 1️⃣ Install kokoro
 !pip install -q kokoro>=0.3.1 soundfile
@@ -59,6 +62,8 @@ The sky above the port was the color of television, tuned to a dead channel.
 It was a Sprawl voice and a Sprawl joke. The Chatsubo was a bar for professional expatriates; you could drink there for a week and never hear two words in Japanese.
 
 These were to have an enormous impact, not only because they were associated with Constantine, but also because, as in so many other areas, the decisions taken by Constantine (or in his name) were to have great significance for centuries to come. One of the main issues was the shape that Christian churches were to take, since there was not, apparently, a tradition of monumental church buildings when Constantine decided to help the Christian church build a series of truly spectacular structures. The main form that these churches took was that of the basilica, a multipurpose rectangular structure, based ultimately on the earlier Greek stoa, which could be found in most of the great cities of the empire. Christianity, unlike classical polytheism, needed a large interior space for the celebration of its religious services, and the basilica aptly filled that need. We naturally do not know the degree to which the emperor was involved in the design of new churches, but it is tempting to connect this with the secular basilica that Constantine completed in the Roman forum (the so-called Basilica of Maxentius) and the one he probably built in Trier, in connection with his residence in the city at a time when he was still caesar.
+
+[Kokoro](/kˈOkəɹO/) is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, [Kokoro](/kˈOkəɹO/) can be deployed anywhere from production environments to personal projects.
 '''
 # text = '「もしおれがただ偶然、そしてこうしようというつもりでなくここに立っているのなら、ちょっとばかり絶望するところだな」と、そんなことが彼の頭に思い浮かんだ。'
 # text = '中國人民不信邪也不怕邪，不惹事也不怕事，任何外國不要指望我們會拿自己的核心利益做交易，不要指望我們會吞下損害我國主權、安全、發展利益的苦果！'
@@ -70,7 +75,7 @@ These were to have an enormous impact, not only because they were associated wit
 
 # 4️⃣ Generate, display, and save audio files in a loop.
 generator = pipeline(
-    text, voice='af_bella', # <= change voice here
+    text, voice='af_heart', # <= change voice here
     speed=1, split_pattern=r'\n+'
 )
 for i, (gs, ps, audio) in enumerate(generator):

SAMPLES.md

@@ -0,0 +1,48 @@
+### HEARME
+> Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects.
+<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/HEARME.wav" type="audio/wav"></audio>
+```
+kˈOkəɹO ɪz ɐn ˈOpᵊnwˌAt tˌitˌiˈɛs mˈɑdᵊl wɪð ˈATi tˈu mˈɪljᵊn pəɹˈæməTəɹz. dəspˈIt ɪts lˈItwˌAt ˈɑɹkətˌɛkʧəɹ, ɪt dəlˈɪvəɹz kˈɑmpəɹəbᵊl kwˈɑləTi tə lˈɑɹʤəɹ mˈɑdᵊlz wˌIl bˈiɪŋ səɡnˈɪfəkəntli fˈæstəɹ ænd mˈɔɹ kˈɔstəfˌɪʃənt. wˌɪð əpˌæʧilˈIsᵊnst wˈAts, kˈOkəɹO kæn bi dəplˈYd ˈɛniwˌɛɹ fɹʌm pɹədˈʌkʃən ənvˈIɹənmᵊnts tə pˈɜɹsᵊnəl pɹˈɑʤˌɛkts.
+```
+
+### af_heart_0
+> The sky above the port was the color of television, tuned to a dead channel.
+<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/af_heart_0.wav" type="audio/wav"></audio>
+```
+ðə skˈI əbˈʌv ðə pˈɔɹt wʌz ðə kˈʌləɹ ʌv tˈɛləvˌɪʒən, tˈund tə ɐ dˈɛd ʧˈænᵊl.
+```
+
+### af_heart_1
+> "It's not like I'm using," Case heard someone say, as he shouldered his way through the crowd around the door of the Chat. "It's like my body's developed this massive drug deficiency."
+<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/af_heart_1.wav" type="audio/wav"></audio>
+```
+“ˌɪts nˌɑt lˈIk ˌIm jˈuzɪŋ,” kˈAs hˈɜɹd sˈʌmwˌʌn sˈA, æz hi ʃˈOldəɹd hɪz wˈA θɹu ðə kɹˈWd əɹˈWnd ðə dˈɔɹ ʌv ðə ʧˈæt. “ˌɪts lˈIk mI bˈɑdiz dəvˈɛləpt ðɪs mˈæsɪv dɹˈʌɡ dəfˈɪʃənsi.”
+```
+
+### af_heart_2
+> It was a Sprawl voice and a Sprawl joke. The Chatsubo was a bar for professional expatriates; you could drink there for a week and never hear two words in Japanese.
+<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/af_heart_2.wav" type="audio/wav"></audio>
+```
+ˌɪt wʌz ɐ spɹˈɔl vˈYs ænd ɐ spɹˈɔl ʤˈOk. ðə ʧætsˈubO wʌz ɐ bˈɑɹ fɔɹ pɹəfˈɛʃᵊnəl ɛkspˈAtɹiəts; ju kʊd dɹˈɪŋk ðɛɹ fɔɹ ɐ wˈik ænd nˈɛvəɹ hˈɪɹ tˈu wˈɜɹdz ɪn ʤˌæpənˈiz.
+```
+
+### af_heart_3
+> These were to have an enormous impact, not only because they were associated with Constantine, but also because, as in so many other areas, the decisions taken by Constantine (or in his name) were to have great significance for centuries to come. One of the main issues was the shape that Christian churches were to take, since there was not, apparently, a tradition of monumental church buildings when Constantine decided to help the Christian church build a series of truly spectacular structures.
+<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/af_heart_3.wav" type="audio/wav"></audio>
+```
+ðˌiz wɜɹ tə hæv ɐn ɪnˈɔɹməs ˈɪmpˌækt, nˌɑt ˈOnli bəkˈʌz ðA wɜɹ əsˈOsiˌATᵻd wɪð kˈɑnstəntˌin, bˌʌt ˈɔlsO bəkˈʌz, æz ɪn sˌO mˈɛni ˈʌðəɹ ˈɛɹiəz, ðə dəsˈɪʒᵊnz tˈAkən bI kˈɑnstəntˌin (ɔɹ ɪn hɪz nˈAm) wɜɹ tə hæv ɡɹˈAt səɡnˈɪfəkᵊns fɔɹ sˈɛnʧəɹiz tə kˈʌm. wˈʌn ʌv ðə mˈAn ˈɪʃjuz wʌz ðə ʃˈAp ðæt kɹˈɪsʧən ʧˈɜɹʧᵻz wɜɹ tə tˈAk, sˈɪns ðɛɹ wʌz nˌɑt, əpˈɛɹəntli, ɐ tɹədˈɪʃən ʌv mˌɑnjəmˈɛntᵊl ʧˈɜɹʧ bˈɪldɪŋz wˌɛn kˈɑnstəntˌin dəsˈIdᵻd tə hˈɛlp ðə kɹˈɪsʧən ʧˈɜɹʧ bˈɪld ɐ sˈɪɹiz ʌv tɹˈuli spɛktˈækjələɹ stɹˈʌkʧəɹz.
+```
+
+### af_heart_4
+> The main form that these churches took was that of the basilica, a multipurpose rectangular structure, based ultimately on the earlier Greek stoa, which could be found in most of the great cities of the empire. Christianity, unlike classical polytheism, needed a large interior space for the celebration of its religious services, and the basilica aptly filled that need.
+<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/af_heart_4.wav" type="audio/wav"></audio>
+```
+ðə mˈAn fˈɔɹm ðæt ðiz ʧˈɜɹʧᵻz tˈʊk wʌz ðæt ʌv ðə bəsˈɪləkə, ɐ mˌʌltipˈɜɹpəs ɹɛktˈæŋɡjələɹ stɹˈʌkʧəɹ, bˈAst ˈʌltəmətli ˌɔn ði ˈɜɹliəɹ ɡɹˈik stˈOə, wˌɪʧ kʊd bi fˈWnd ɪn mˈOst ʌv ðə ɡɹˈAt sˈɪTiz ʌv ði ˈɛmpˌIəɹ. kɹˌɪsʧiˈænəTi, ˌʌnlˈIk klˈæsəkᵊl pˈɑliθiˌɪzəm, nˈidᵻd ɐ lˈɑɹʤ ɪntˈɪɹiəɹ spˈAs fɔɹ ðə sˌɛləbɹˈAʃən ʌv ɪts ɹəlˈɪʤəs sˈɜɹvəsᵻz, ænd ðə bəsˈɪləkə ˈæptli fˈɪld ðæt nˈid.
+```
+
+### af_heart_5
+> We naturally do not know the degree to which the emperor was involved in the design of new churches, but it is tempting to connect this with the secular basilica that Constantine completed in the Roman forum (the so-called Basilica of Maxentius) and the one he probably built in Trier, in connection with his residence in the city at a time when he was still caesar.
+<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/af_heart_5.wav" type="audio/wav"></audio>
+```
+wˌi nˈæʧəɹəli dˈu nˌɑt nˈO ðə dəɡɹˈi tə wˌɪʧ ði ˈɛmpəɹəɹ wʌz ɪnvˈɑlvd ɪn ðə dəzˈIn ʌv nˈu ʧˈɜɹʧᵻz, bˌʌt ɪt ɪz tˈɛmptɪŋ tə kənˈɛkt ðɪs wɪð ðə sˈɛkjələɹ bəsˈɪləkə ðæt kˈɑnstəntˌin kəmplˈiTᵻd ɪn ðə ɹˈOmən fˈɔɹəm (ðə sˌOkˈɔld bəsˈɪləkə ʌv mæksˈɛntiəs) ænd ðə wˈʌn hi pɹˈɑbəbli bˈɪlt ɪn tɹˈɪɹ, ɪn kənˈɛkʃən wɪð hɪz ɹˈɛzədᵊns ɪn ðə sˈɪTi æt ɐ tˈIm wˌɛn hi wʌz stˈɪl sˈizəɹ.
+```