pvleopard 2.0.1__tar.gz → 2.0.4__tar.gz

{pvleopard-2.0.1 → pvleopard-2.0.4}/MANIFEST.in

@@ -7,5 +7,4 @@ include pvleopard/lib/common/leopard_params.pv
 recursive-include pvleopard/lib/linux *
 recursive-include pvleopard/lib/mac *
 recursive-include pvleopard/lib/windows *
-recursive-include pvleopard/lib/jetson *
 recursive-include pvleopard/lib/raspberry-pi *

pvleopard-2.0.4/PKG-INFO

@@ -0,0 +1,104 @@
+Metadata-Version: 2.1
+Name: pvleopard
+Version: 2.0.4
+Summary: Leopard Speech-to-Text Engine.
+Home-page: https://github.com/Picovoice/leopard
+Author: Picovoice
+Author-email: hello@picovoice.ai
+Keywords: Speech-to-Text,Speech Recognition,Voice Recognition,ASR,Automatic Speech Recognition
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+
+# Leopard Binding for Python
+
+## Leopard Speech-to-Text Engine
+
+Made in Vancouver, Canada by [Picovoice](https://picovoice.ai)
+
+Leopard is an on-device speech-to-text engine. Leopard is:
+
+- Private; All voice processing runs locally.
+- [Accurate](https://picovoice.ai/docs/benchmark/stt/)
+- [Compact and Computationally-Efficient](https://github.com/Picovoice/speech-to-text-benchmark#rtf)
+- Cross-Platform:
+  - Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64, arm64)
+  - Android and iOS
+  - Chrome, Safari, Firefox, and Edge
+  - Raspberry Pi (3, 4, 5)
+
+## Compatibility
+
+- Python 3.8+
+- Runs on Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64, arm64), and Raspberry Pi (3, 4, 5).
+
+## Installation
+
+```console
+pip3 install pvleopard
+```
+
+## AccessKey
+
+Leopard requires a valid Picovoice `AccessKey` at initialization. `AccessKey` acts as your credentials when using Leopard SDKs.
+You can get your `AccessKey` for free. Make sure to keep your `AccessKey` secret.
+Signup or Login to [Picovoice Console](https://console.picovoice.ai/) to get your `AccessKey`.
+
+## Usage
+
+Create an instance of the engine and transcribe an audio file:
+
+```python
+import pvleopard
+
+leopard = pvleopard.create(access_key='${ACCESS_KEY}')
+
+transcript, words = leopard.process_file('${AUDIO_FILE_PATH}')
+print(transcript)
+for word in words:
+    print(
+      "{word=\"%s\" start_sec=%.2f end_sec=%.2f confidence=%.2f speaker_tag=%d}"
+      % (word.word, word.start_sec, word.end_sec, word.confidence, word.speaker_tag))
+```
+
+Replace `${ACCESS_KEY}` with yours obtained from [Picovoice Console](https://console.picovoice.ai/) and
+`${AUDIO_FILE_PATH}` to the path an audio file.
+
+Finally, when done be sure to explicitly release the resources:
+```python
+leopard.delete()
+```
+
+### Language Model
+
+The Leopard Python SDK comes preloaded with a default English language model (`.pv` file).
+Default models for other supported languages can be found in [lib/common](../../lib/common).
+
+Create custom language models using the [Picovoice Console](https://console.picovoice.ai/). Here you can train
+language models with custom vocabulary and boost words in the existing vocabulary.
+
+Pass in the `.pv` file via the `model_path` argument:
+```python
+leopard = pvleopard.create(
+    access_key='${ACCESS_KEY}',
+    model_path='${MODEL_FILE_PATH}')
+```
+
+### Word Metadata
+
+Along with the transcript, Leopard returns metadata for each transcribed word. Available metadata items are:
+
+- **Start Time:** Indicates when the word started in the transcribed audio. Value is in seconds.
+- **End Time:** Indicates when the word ended in the transcribed audio. Value is in seconds.
+- **Confidence:** Leopard's confidence that the transcribed word is accurate. It is a number within `[0, 1]`.
+- **Speaker Tag:** If speaker diarization is enabled on initialization, the speaker tag is a non-negative integer identifying unique speakers, with `0` reserved for unknown speakers. If speaker diarization is not enabled, the value will always be `-1`.
+
+## Demos
+
+[pvleoparddemo](https://pypi.org/project/pvleoparddemo/) provides command-line utilities for processing audio using
+Leopard.

{pvleopard-2.0.1 → pvleopard-2.0.4}/README.md

@@ -10,15 +10,15 @@ Leopard is an on-device speech-to-text engine. Leopard is:
 - [Accurate](https://picovoice.ai/docs/benchmark/stt/)
 - [Compact and Computationally-Efficient](https://github.com/Picovoice/speech-to-text-benchmark#rtf)
 - Cross-Platform:
-  - Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64)
+  - Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64, arm64)
   - Android and iOS
   - Chrome, Safari, Firefox, and Edge
-  - Raspberry Pi (4, 3) and NVIDIA Jetson Nano
+  - Raspberry Pi (3, 4, 5)
 
 ## Compatibility
 
-- Python 3.5+
-- Runs on Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64), Raspberry Pi (4, 3), and NVIDIA Jetson Nano.
+- Python 3.8+
+- Runs on Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64, arm64), and Raspberry Pi (3, 4, 5).
 
 ## Installation
 
@@ -32,7 +32,7 @@ Leopard requires a valid Picovoice `AccessKey` at initialization. `AccessKey` ac
 You can get your `AccessKey` for free. Make sure to keep your `AccessKey` secret.
 Signup or Login to [Picovoice Console](https://console.picovoice.ai/) to get your `AccessKey`.
 
-### Usage
+## Usage
 
 Create an instance of the engine and transcribe an audio file:
 
@@ -41,23 +41,23 @@ import pvleopard
 
 leopard = pvleopard.create(access_key='${ACCESS_KEY}')
 
-transcript, words = leopard.process_file('${AUDIO_PATH}')
+transcript, words = leopard.process_file('${AUDIO_FILE_PATH}')
 print(transcript)
 for word in words:
     print(
-      "{word=\"%s\" start_sec=%.2f end_sec=%.2f confidence=%.2f}"
-      % (word.word, word.start_sec, word.end_sec, word.confidence))
+      "{word=\"%s\" start_sec=%.2f end_sec=%.2f confidence=%.2f speaker_tag=%d}"
+      % (word.word, word.start_sec, word.end_sec, word.confidence, word.speaker_tag))
 ```
 
 Replace `${ACCESS_KEY}` with yours obtained from [Picovoice Console](https://console.picovoice.ai/) and
-`${AUDIO_PATH}` to the path an audio file.
+`${AUDIO_FILE_PATH}` to the path an audio file.
 
 Finally, when done be sure to explicitly release the resources:
 ```python
 leopard.delete()
 ```
 
-## Language Model
+### Language Model
 
 The Leopard Python SDK comes preloaded with a default English language model (`.pv` file).
 Default models for other supported languages can be found in [lib/common](../../lib/common).
@@ -69,9 +69,18 @@ Pass in the `.pv` file via the `model_path` argument:
 ```python
 leopard = pvleopard.create(
     access_key='${ACCESS_KEY}',
-    model_path='${MODEL_PATH}')
+    model_path='${MODEL_FILE_PATH}')
 ```
 
+### Word Metadata
+
+Along with the transcript, Leopard returns metadata for each transcribed word. Available metadata items are:
+
+- **Start Time:** Indicates when the word started in the transcribed audio. Value is in seconds.
+- **End Time:** Indicates when the word ended in the transcribed audio. Value is in seconds.
+- **Confidence:** Leopard's confidence that the transcribed word is accurate. It is a number within `[0, 1]`.
+- **Speaker Tag:** If speaker diarization is enabled on initialization, the speaker tag is a non-negative integer identifying unique speakers, with `0` reserved for unknown speakers. If speaker diarization is not enabled, the value will always be `-1`.
+
 ## Demos
 
 [pvleoparddemo](https://pypi.org/project/pvleoparddemo/) provides command-line utilities for processing audio using

{pvleopard-2.0.1 → pvleopard-2.0.4}/pvleopard/_util.py

@@ -1,5 +1,5 @@
 #
-# Copyright 2022-2023 Picovoice Inc.
+# Copyright 2022-2024 Picovoice Inc.
 #
 # You may not use this file except in compliance with the license. A copy of the license is located in the "LICENSE"
 # file accompanying this source.
@@ -37,16 +37,21 @@ def _linux_machine():
 
     if '0xd03' == cpu_part:
         return 'cortex-a53' + arch_info
-    elif '0xd07' == cpu_part:
-        return 'cortex-a57' + arch_info
     elif '0xd08' == cpu_part:
         return 'cortex-a72' + arch_info
+    elif "0xd0b" == cpu_part:
+        return "cortex-a76" + arch_info
     else:
         raise NotImplementedError("Unsupported CPU: `%s`." % cpu_part)
 
 
-_RASPBERRY_PI_MACHINES = {'cortex-a53', 'cortex-a72', 'cortex-a53-aarch64', 'cortex-a72-aarch64'}
-_JETSON_MACHINES = {'cortex-a57-aarch64'}
+_RASPBERRY_PI_MACHINES = {
+    "cortex-a53",
+    "cortex-a72",
+    "cortex-a76",
+    "cortex-a53-aarch64",
+    "cortex-a72-aarch64",
+    "cortex-a76-aarch64"}
 
 
 def default_library_path(relative):
@@ -59,15 +64,16 @@ def default_library_path(relative):
         linux_machine = _linux_machine()
         if linux_machine == 'x86_64':
             return os.path.join(os.path.dirname(__file__), relative, 'lib/linux/x86_64/libpv_leopard.so')
-        elif linux_machine in _JETSON_MACHINES:
-            return os.path.join(os.path.dirname(__file__), relative, 'lib/jetson/%s/libpv_leopard.so' % linux_machine)
         elif linux_machine in _RASPBERRY_PI_MACHINES:
             return os.path.join(
                 os.path.dirname(__file__),
                 relative,
                 'lib/raspberry-pi/%s/libpv_leopard.so' % linux_machine)
     elif platform.system() == 'Windows':
-        return os.path.join(os.path.dirname(__file__), relative, 'lib/windows/amd64/libpv_leopard.dll')
+        if platform.machine().lower() == 'amd64':
+            return os.path.join(os.path.dirname(__file__), relative, 'lib/windows/amd64/libpv_leopard.dll')
+        elif platform.machine().lower() == 'arm64':
+            return os.path.join(os.path.dirname(__file__), relative, 'lib/windows/arm64/libpv_leopard.dll')
 
     raise NotImplementedError('Unsupported platform.')
 

pvleopard-2.0.4/pvleopard.egg-info/PKG-INFO

@@ -0,0 +1,104 @@
+Metadata-Version: 2.1
+Name: pvleopard
+Version: 2.0.4
+Summary: Leopard Speech-to-Text Engine.
+Home-page: https://github.com/Picovoice/leopard
+Author: Picovoice
+Author-email: hello@picovoice.ai
+Keywords: Speech-to-Text,Speech Recognition,Voice Recognition,ASR,Automatic Speech Recognition
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+
+# Leopard Binding for Python
+
+## Leopard Speech-to-Text Engine
+
+Made in Vancouver, Canada by [Picovoice](https://picovoice.ai)
+
+Leopard is an on-device speech-to-text engine. Leopard is:
+
+- Private; All voice processing runs locally.
+- [Accurate](https://picovoice.ai/docs/benchmark/stt/)
+- [Compact and Computationally-Efficient](https://github.com/Picovoice/speech-to-text-benchmark#rtf)
+- Cross-Platform:
+  - Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64, arm64)
+  - Android and iOS
+  - Chrome, Safari, Firefox, and Edge
+  - Raspberry Pi (3, 4, 5)
+
+## Compatibility
+
+- Python 3.8+
+- Runs on Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64, arm64), and Raspberry Pi (3, 4, 5).
+
+## Installation
+
+```console
+pip3 install pvleopard
+```
+
+## AccessKey
+
+Leopard requires a valid Picovoice `AccessKey` at initialization. `AccessKey` acts as your credentials when using Leopard SDKs.
+You can get your `AccessKey` for free. Make sure to keep your `AccessKey` secret.
+Signup or Login to [Picovoice Console](https://console.picovoice.ai/) to get your `AccessKey`.
+
+## Usage
+
+Create an instance of the engine and transcribe an audio file:
+
+```python
+import pvleopard
+
+leopard = pvleopard.create(access_key='${ACCESS_KEY}')
+
+transcript, words = leopard.process_file('${AUDIO_FILE_PATH}')
+print(transcript)
+for word in words:
+    print(
+      "{word=\"%s\" start_sec=%.2f end_sec=%.2f confidence=%.2f speaker_tag=%d}"
+      % (word.word, word.start_sec, word.end_sec, word.confidence, word.speaker_tag))
+```
+
+Replace `${ACCESS_KEY}` with yours obtained from [Picovoice Console](https://console.picovoice.ai/) and
+`${AUDIO_FILE_PATH}` to the path an audio file.
+
+Finally, when done be sure to explicitly release the resources:
+```python
+leopard.delete()
+```
+
+### Language Model
+
+The Leopard Python SDK comes preloaded with a default English language model (`.pv` file).
+Default models for other supported languages can be found in [lib/common](../../lib/common).
+
+Create custom language models using the [Picovoice Console](https://console.picovoice.ai/). Here you can train
+language models with custom vocabulary and boost words in the existing vocabulary.
+
+Pass in the `.pv` file via the `model_path` argument:
+```python
+leopard = pvleopard.create(
+    access_key='${ACCESS_KEY}',
+    model_path='${MODEL_FILE_PATH}')
+```
+
+### Word Metadata
+
+Along with the transcript, Leopard returns metadata for each transcribed word. Available metadata items are:
+
+- **Start Time:** Indicates when the word started in the transcribed audio. Value is in seconds.
+- **End Time:** Indicates when the word ended in the transcribed audio. Value is in seconds.
+- **Confidence:** Leopard's confidence that the transcribed word is accurate. It is a number within `[0, 1]`.
+- **Speaker Tag:** If speaker diarization is enabled on initialization, the speaker tag is a non-negative integer identifying unique speakers, with `0` reserved for unknown speakers. If speaker diarization is not enabled, the value will always be `-1`.
+
+## Demos
+
+[pvleoparddemo](https://pypi.org/project/pvleoparddemo/) provides command-line utilities for processing audio using
+Leopard.

{pvleopard-2.0.1 → pvleopard-2.0.4}/pvleopard.egg-info/SOURCES.txt

@@ -11,7 +11,6 @@ pvleopard.egg-info/SOURCES.txt
 pvleopard.egg-info/dependency_links.txt
 pvleopard.egg-info/top_level.txt
 pvleopard/lib/common/leopard_params.pv
-pvleopard/lib/jetson/cortex-a57-aarch64/libpv_leopard.so
 pvleopard/lib/linux/x86_64/libpv_leopard.so
 pvleopard/lib/mac/arm64/libpv_leopard.dylib
 pvleopard/lib/mac/x86_64/libpv_leopard.dylib
@@ -19,4 +18,7 @@ pvleopard/lib/raspberry-pi/cortex-a53/libpv_leopard.so
 pvleopard/lib/raspberry-pi/cortex-a53-aarch64/libpv_leopard.so
 pvleopard/lib/raspberry-pi/cortex-a72/libpv_leopard.so
 pvleopard/lib/raspberry-pi/cortex-a72-aarch64/libpv_leopard.so
-pvleopard/lib/windows/amd64/libpv_leopard.dll
+pvleopard/lib/raspberry-pi/cortex-a76/libpv_leopard.so
+pvleopard/lib/raspberry-pi/cortex-a76-aarch64/libpv_leopard.so
+pvleopard/lib/windows/amd64/libpv_leopard.dll
+pvleopard/lib/windows/arm64/libpv_leopard.dll

{pvleopard-2.0.1 → pvleopard-2.0.4}/setup.py

@@ -1,5 +1,5 @@
 #
-# Copyright 2022-2023 Picovoice Inc.
+# Copyright 2022-2024 Picovoice Inc.
 #
 # You may not use this file except in compliance with the license. A copy of the license is located in the "LICENSE"
 # file accompanying this source.
@@ -15,7 +15,7 @@ import shutil
 import setuptools
 
 INCLUDE_FILES = ('../../LICENSE', '__init__.py', '_factory.py', '_leopard.py', '_util.py')
-INCLUDE_LIBS = ('linux', 'mac', 'windows', 'jetson', 'raspberry-pi')
+INCLUDE_LIBS = ('linux', 'mac', 'windows', 'raspberry-pi')
 
 os.system('git clean -dfx')
 
@@ -48,7 +48,7 @@ with open(os.path.join(os.path.dirname(__file__), 'README.md'), 'r') as f:
 
 setuptools.setup(
     name="pvleopard",
-    version="2.0.1",
+    version="2.0.4",
     author="Picovoice",
     author_email="hello@picovoice.ai",
     description="Leopard Speech-to-Text Engine.",
@@ -65,6 +65,6 @@ setuptools.setup(
         "Programming Language :: Python :: 3",
         "Topic :: Multimedia :: Sound/Audio :: Speech"
     ],
-    python_requires='>=3.5',
+    python_requires='>=3.8',
     keywords="Speech-to-Text, Speech Recognition, Voice Recognition, ASR, Automatic Speech Recognition",
 )

pvleopard-2.0.1/PKG-INFO

@@ -1,97 +0,0 @@
-Metadata-Version: 2.1
-Name: pvleopard
-Version: 2.0.1
-Summary: Leopard Speech-to-Text Engine.
-Home-page: https://github.com/Picovoice/leopard
-Author: Picovoice
-Author-email: hello@picovoice.ai
-License: UNKNOWN
-Description: # Leopard Binding for Python
-        
-        ## Leopard Speech-to-Text Engine
-        
-        Made in Vancouver, Canada by [Picovoice](https://picovoice.ai)
-        
-        Leopard is an on-device speech-to-text engine. Leopard is:
-        
-        - Private; All voice processing runs locally.
-        - [Accurate](https://picovoice.ai/docs/benchmark/stt/)
-        - [Compact and Computationally-Efficient](https://github.com/Picovoice/speech-to-text-benchmark#rtf)
-        - Cross-Platform:
-          - Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64)
-          - Android and iOS
-          - Chrome, Safari, Firefox, and Edge
-          - Raspberry Pi (4, 3) and NVIDIA Jetson Nano
-        
-        ## Compatibility
-        
-        - Python 3.5+
-        - Runs on Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64), Raspberry Pi (4, 3), and NVIDIA Jetson Nano.
-        
-        ## Installation
-        
-        ```console
-        pip3 install pvleopard
-        ```
-        
-        ## AccessKey
-        
-        Leopard requires a valid Picovoice `AccessKey` at initialization. `AccessKey` acts as your credentials when using Leopard SDKs.
-        You can get your `AccessKey` for free. Make sure to keep your `AccessKey` secret.
-        Signup or Login to [Picovoice Console](https://console.picovoice.ai/) to get your `AccessKey`.
-        
-        ### Usage
-        
-        Create an instance of the engine and transcribe an audio file:
-        
-        ```python
-        import pvleopard
-        
-        leopard = pvleopard.create(access_key='${ACCESS_KEY}')
-        
-        transcript, words = leopard.process_file('${AUDIO_PATH}')
-        print(transcript)
-        for word in words:
-            print(
-              "{word=\"%s\" start_sec=%.2f end_sec=%.2f confidence=%.2f}"
-              % (word.word, word.start_sec, word.end_sec, word.confidence))
-        ```
-        
-        Replace `${ACCESS_KEY}` with yours obtained from [Picovoice Console](https://console.picovoice.ai/) and
-        `${AUDIO_PATH}` to the path an audio file.
-        
-        Finally, when done be sure to explicitly release the resources:
-        ```python
-        leopard.delete()
-        ```
-        
-        ## Language Model
-        
-        The Leopard Python SDK comes preloaded with a default English language model (`.pv` file).
-        Default models for other supported languages can be found in [lib/common](../../lib/common).
-        
-        Create custom language models using the [Picovoice Console](https://console.picovoice.ai/). Here you can train
-        language models with custom vocabulary and boost words in the existing vocabulary.
-        
-        Pass in the `.pv` file via the `model_path` argument:
-        ```python
-        leopard = pvleopard.create(
-            access_key='${ACCESS_KEY}',
-            model_path='${MODEL_PATH}')
-        ```
-        
-        ## Demos
-        
-        [pvleoparddemo](https://pypi.org/project/pvleoparddemo/) provides command-line utilities for processing audio using
-        Leopard.
-        
-Keywords: Speech-to-Text,Speech Recognition,Voice Recognition,ASR,Automatic Speech Recognition
-Platform: UNKNOWN
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
-Requires-Python: >=3.5
-Description-Content-Type: text/markdown

pvleopard-2.0.1/pvleopard.egg-info/PKG-INFO

@@ -1,97 +0,0 @@
-Metadata-Version: 2.1
-Name: pvleopard
-Version: 2.0.1
-Summary: Leopard Speech-to-Text Engine.
-Home-page: https://github.com/Picovoice/leopard
-Author: Picovoice
-Author-email: hello@picovoice.ai
-License: UNKNOWN
-Description: # Leopard Binding for Python
-        
-        ## Leopard Speech-to-Text Engine
-        
-        Made in Vancouver, Canada by [Picovoice](https://picovoice.ai)
-        
-        Leopard is an on-device speech-to-text engine. Leopard is:
-        
-        - Private; All voice processing runs locally.
-        - [Accurate](https://picovoice.ai/docs/benchmark/stt/)
-        - [Compact and Computationally-Efficient](https://github.com/Picovoice/speech-to-text-benchmark#rtf)
-        - Cross-Platform:
-          - Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64)
-          - Android and iOS
-          - Chrome, Safari, Firefox, and Edge
-          - Raspberry Pi (4, 3) and NVIDIA Jetson Nano
-        
-        ## Compatibility
-        
-        - Python 3.5+
-        - Runs on Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64), Raspberry Pi (4, 3), and NVIDIA Jetson Nano.
-        
-        ## Installation
-        
-        ```console
-        pip3 install pvleopard
-        ```
-        
-        ## AccessKey
-        
-        Leopard requires a valid Picovoice `AccessKey` at initialization. `AccessKey` acts as your credentials when using Leopard SDKs.
-        You can get your `AccessKey` for free. Make sure to keep your `AccessKey` secret.
-        Signup or Login to [Picovoice Console](https://console.picovoice.ai/) to get your `AccessKey`.
-        
-        ### Usage
-        
-        Create an instance of the engine and transcribe an audio file:
-        
-        ```python
-        import pvleopard
-        
-        leopard = pvleopard.create(access_key='${ACCESS_KEY}')
-        
-        transcript, words = leopard.process_file('${AUDIO_PATH}')
-        print(transcript)
-        for word in words:
-            print(
-              "{word=\"%s\" start_sec=%.2f end_sec=%.2f confidence=%.2f}"
-              % (word.word, word.start_sec, word.end_sec, word.confidence))
-        ```
-        
-        Replace `${ACCESS_KEY}` with yours obtained from [Picovoice Console](https://console.picovoice.ai/) and
-        `${AUDIO_PATH}` to the path an audio file.
-        
-        Finally, when done be sure to explicitly release the resources:
-        ```python
-        leopard.delete()
-        ```
-        
-        ## Language Model
-        
-        The Leopard Python SDK comes preloaded with a default English language model (`.pv` file).
-        Default models for other supported languages can be found in [lib/common](../../lib/common).
-        
-        Create custom language models using the [Picovoice Console](https://console.picovoice.ai/). Here you can train
-        language models with custom vocabulary and boost words in the existing vocabulary.
-        
-        Pass in the `.pv` file via the `model_path` argument:
-        ```python
-        leopard = pvleopard.create(
-            access_key='${ACCESS_KEY}',
-            model_path='${MODEL_PATH}')
-        ```
-        
-        ## Demos
-        
-        [pvleoparddemo](https://pypi.org/project/pvleoparddemo/) provides command-line utilities for processing audio using
-        Leopard.
-        
-Keywords: Speech-to-Text,Speech Recognition,Voice Recognition,ASR,Automatic Speech Recognition
-Platform: UNKNOWN
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
-Requires-Python: >=3.5
-Description-Content-Type: text/markdown