let whisperKit = try await WhisperKit()

// Transcribe a single audio file
let results: [TranscriptionResult] = try await whisperKit.transcribe(
    audioPath: "path/to/audio.wav"
)

for result in results {
    print("Text: \(result.text)")
    print("Language: \(result.language)")
}

// Audio must be 16kHz mono float array
let audioArray: [Float] = loadAudioSamples()

let results = try await whisperKit.transcribe(
    audioArray: audioArray
)

var options = DecodingOptions(
    verbose: true,
    task: .transcribe,           // or .translate for English translation
    language: "en",              // Specify language or nil for auto-detect
    temperature: 0.0,            // 0.0 for greedy, >0 for sampling
    wordTimestamps: true,        // Enable word-level timestamps
    skipSpecialTokens: true      // Remove special tokens from output
)

let results = try await whisperKit.transcribe(
    audioPath: "audio.wav",
    decodeOptions: options
)

let audioPaths = [
    "audio1.wav",
    "audio2.wav",
    "audio3.wav"
]

let results = await whisperKit.transcribe(
    audioPaths: audioPaths,
    decodeOptions: options
)

// Results is [[TranscriptionResult]?] - one array per file
for (index, result) in results.enumerated() {
    if let transcriptions = result {
        print("File \(index): \(transcriptions.first?.text ?? "")")
    }
}

let results = await whisperKit.transcribeWithResults(
    audioPaths: audioPaths
)

for (index, result) in results.enumerated() {
    switch result {
    case .success(let transcriptions):
        print("Success: \(transcriptions.first?.text ?? "")")
    case .failure(let error):
        print("Error transcribing file \(index): \(error)")
    }
}

let result: TranscriptionResult = results.first!

// Full transcribed text
print(result.text)

// Detected language
print(result.language)

// Individual segments with timestamps
for segment in result.segments {
    print("[\(segment.start)s - \(segment.end)s]: \(segment.text)")
    
    // Word-level timestamps (if enabled)
    if let words = segment.words {
        for word in words {
            print("  \(word.word): \(word.start)s - \(word.end)s")
        }
    }
}

// Performance timings
result.logTimings()

let (language, probabilities) = try await whisperKit.detectLanguage(
    audioPath: "audio.wav"
)

print("Detected language: \(language)")
for (lang, prob) in probabilities.sorted(by: { $0.value > $1.value }).prefix(5) {
    print("  \(lang): \(prob)")
}

let results = try await whisperKit.transcribe(
    audioPath: "audio.wav",
    decodeOptions: options,
    callback: { progress in
        print("Window \(progress.windowId): \(progress.text)")
        print("Tokens: \(progress.tokens.count)")
        
        // Return false to cancel early
        return shouldContinue ? nil : false
    }
)

var options = DecodingOptions(
    clipTimestamps: [0.0, 30.0, 60.0]  // Transcribe 0-30s and 60s onwards
)

let results = try await whisperKit.transcribe(
    audioPath: "audio.wav",
    decodeOptions: options
)

let promptTokens = whisperKit.tokenizer?.encode(text: "Welcome to the conference")

var options = DecodingOptions(
    promptTokens: promptTokens
)

var options = DecodingOptions(
    temperature: 0.0,
    temperatureIncrementOnFallback: 0.2,  // Increase by 0.2 each retry
    temperatureFallbackCount: 5            // Try up to 5 times
)